© 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. 12-GEMMASCOPE-RES-16K
    6. 8460
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and symbols in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.80
    MessageOf
    -0.73
    principalColumn
    -0.67
    DoubleQuotes
    -0.65
    SourceChecksum
    -0.65
    IsContent
    -0.62
     tribune
    -0.62
    actionMode
    -0.58
    ActionMode
    -0.58
     Liquids
    -0.57
    POSITIVE LOGITS
    ximadamente
    0.50
    mostly
    0.49
    ="@+
    0.48
    だらけ
    0.47
     mostly
    0.47
    ngdoc
    0.45
     daar
    0.45
     vooral
    0.44
    umably
    0.43
    ┻
    0.43
    Activations Density 0.963%

    No Known Activations