© 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. 12440
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cover" and its variations, indicating attention to themes of concealment or protection

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

    the word "cover" in various contexts.

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

    the verb "cover" and related words like "covers" or "covered".

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

    references to the “cover” root in any form, including its inflections, derivations, and compounds.

    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
    angun
    -0.37
    ां
    -0.35
    Ậ
    -0.33
     Gud
    -0.32
     Friar
    -0.32
     Eins
    -0.32
    pend
    -0.32
     Sheng
    -0.31
    Eins
    -0.31
    kür
    -0.31
    POSITIVE LOGITS
     Cover
    1.09
    Cover
    1.05
     COVER
    0.99
     cover
    0.99
    cover
    0.96
    Covers
    0.92
    Covered
    0.90
    COVER
    0.89
    coverage
    0.88
     Covers
    0.88
    Activations Density 0.141%

    No Known Activations