Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 2985
    Prev
    Next
    INDEX
    Explanations

    expressions related to fitting or compatibility, especially in terms of size or suitability

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

    "fit" or slight variations

    np_acts-logits-general · gemini-2.0-flash

    fit or fitting suitability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.80
    حياته
    -0.77
    dafx
    -0.77
    GEBURTSDATUM
    -0.73
     Efq
    -0.73
     albedo
    -0.72
     للمعارف
    -0.72
    principalColumn
    -0.72
    Santé
    -0.70
    djangoproject
    -0.69
    POSITIVE LOGITS
    Fits
    1.20
     Fits
    1.19
    fit
    1.17
     fits
    1.15
     FIT
    1.13
     fit
    1.10
    Fit
    1.10
     Fit
    1.09
    fits
    1.07
     Fitz
    1.04
    Activations Density 0.160%

    No Known Activations