© 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. 4-GEMMASCOPE-RES-16K
    11. 12679
    Prev
    Next
    INDEX
    Explanations

    identifiers and syntax elements typical in programming languages, particularly related to policies and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.87
    IntoConstraints
    -0.86
    WaitGroup
    -0.84
    InSection
    -0.81
    DebuggerNonUser
    -0.79
    DockStyle
    -0.72
     BorderRadius
    -0.69
    StoryboardSegue
    -0.65
    WithIdentifier
    -0.65
    ReusableCell
    -0.64
    POSITIVE LOGITS
    //
    0.57
    MigrationBuilder
    0.56
    enoord
    0.56
    jsonwebtoken
    0.52
     Virol
    0.51
    ագրություններ
    0.50
     Redwood
    0.50
     scientifique
    0.50
     goggles
    0.49
    Slf
    0.48
    Activations Density 2.250%

    No Known Activations