© 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. 959
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in programming or code-related contexts

    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
    fillType
    -0.82
    LookAnd
    -0.81
     صوتيه
    -0.80
    quelize
    -0.76
     Roskov
    -0.75
     useAppContext
    -0.74
    انيف
    -0.72
     دیکھیے
    -0.72
    rinfo
    -0.71
     unknownFields
    -0.71
    POSITIVE LOGITS
    iel
    0.47
    ่อย
    0.45
    vara
    0.41
    obald
    0.40
    ont
    0.38
    ă
    0.38
    et
    0.37
     intervening
    0.37
    erv
    0.36
    単
    0.36
    Activations Density 0.668%

    No Known Activations