© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 7438
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ComVisible
    -0.89
     تضيفلها
    -0.84
     ostavi
    -0.83
     Werth
    -0.80
    zzlies
    -0.76
     Cornelia
    -0.76
    Enrico
    -0.74
     Enrico
    -0.74
    SequentialGroup
    -0.74
     >(
    -0.73
    POSITIVE LOGITS
    2
    1.23
    nd
    0.86
    ₂
    0.82
    २
    0.77
     Twain
    0.77
    2
    0.75
     twos
    0.75
    zwe
    0.74
    ২
    0.72
     Boyd
    0.69
    Activations Density 0.652%

    No Known Activations