© 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. 10331
    Prev
    Next
    INDEX
    Explanations

    elements of dates, times, and specific references to articles or headlines

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

    possessive apostrophes and contractions (particularly the apostrophe-s pattern indicating ownership or shortened words).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    bkz
    -0.41
    笑
    -0.38
    destroyAll
    -0.37
     հղումներ
    -0.36
    NewReader
    -0.36
    UnifiedTopology
    -0.35
    InteropServices
    -0.35
     विश्वसनीयता
    -0.34
    ishu
    -0.34
    LEncoder
    -0.34
    POSITIVE LOGITS
     NavController
    0.52
     zoude
    0.48
    httphttps
    0.47
    uelan
    0.47
    washingtonpost
    0.46
     tartalomajánló
    0.45
    sinki
    0.45
    ]")]
    0.45
    دانشنامهٔ
    0.44
    abetes
    0.44
    Activations Density 0.095%

    No Known Activations