© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13574
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fit" and its variations, indicating suitability or compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases where "fit" or "fits" is used with "into" to describe something belonging to, matching, or being compatible with a category or context.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    the word "fit" followed by a preposition (especially "into", "for", or "in").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    expressions about suitability or compatibility—especially constructions indicating something fits or belongs within a category, purpose, or context.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.45
     NavController
    -0.44
    kező
    -0.42
    RootPath
    -0.38
    Izvori
    -0.38
    قایناق‌لار
    -0.37
    Litteratur
    -0.37
     Вікі
    -0.37
    CharCode
    -0.37
    labus
    -0.37
    POSITIVE LOGITS
     Fit
    0.89
     fit
    0.89
    Fit
    0.74
     FIT
    0.68
     fitted
    0.66
     fitting
    0.66
     fits
    0.66
    Fits
    0.66
    fit
    0.65
    FIT
    0.65
    Activations Density 0.075%

    No Known Activations