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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8053
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cover" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mael
    -0.50
    poietic
    -0.45
    ſt
    -0.44
     Maldonado
    -0.44
     Artis
    -0.44
    mjs
    -0.44
     Martino
    -0.43
    alang
    -0.43
    initialState
    -0.43
     Mahl
    -0.42
    POSITIVE LOGITS
     Cover
    1.60
    Cover
    1.50
     cover
    1.50
     COVER
    1.45
     coverage
    1.44
    cover
    1.41
    coverage
    1.38
     Coverage
    1.38
     Covers
    1.37
     Covering
    1.37
    Activations Density 0.049%

    No Known Activations