© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15058
    Prev
    Next
    INDEX
    Explanations

    code-related syntax, particularly in programming and data structures

    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
    urlopen
    -0.53
    em
    -0.53
    ob
    -0.52
    iv
    -0.52
    ion
    -0.51
    \
    -0.51
    Token
    -0.50
    ্ত
    -0.49
    Item
    -0.47
    U
    -0.47
    POSITIVE LOGITS
    AutoresizingMask
    0.90
    ."</
    0.90
    UnsafeEnabled
    0.88
     cherchés
    0.87
    ratulations
    0.86
    ActionCreators
    0.86
    setVerticalGroup
    0.85
     كومونز
    0.84
    ValueStyle
    0.83
    Viitteet
    0.83
    Activations Density 0.375%

    No Known Activations