© 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. 15067
    Prev
    Next
    INDEX
    Explanations

    elements related to programming interfaces and structures in code documentation

    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
    ServletException
    -0.68
    URLException
    -0.66
    verifyException
    -0.66
    ViewImports
    -0.64
    FunctionFlags
    -0.64
    +#+#
    -0.63
    󠁢
    -0.62
    HostException
    -0.62
    geoning
    -0.62
    ableView
    -0.62
    POSITIVE LOGITS
    ssi
    0.60
    webElementXpaths
    0.56
    abbix
    0.55
    .$_
    0.53
     Petersburg
    0.53
    ändig
    0.52
     Fathers
    0.52
    migrationBuilder
    0.52
     sơ
    0.51
    xFFFFFFFF
    0.51
    Activations Density 0.021%

    No Known Activations