© 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. 2-GEMMASCOPE-RES-16K
    6. 6984
    Prev
    Next
    INDEX
    Explanations

    components related to programming and software assembly attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sproz
    -0.45
     assumed
    -0.43
     assume
    -0.43
     zah
    -0.42
     personalidad
    -0.38
     care
    -0.38
     estimated
    -0.37
     Universitaria
    -0.37
     enemigo
    -0.36
    ásban
    -0.35
    POSITIVE LOGITS
     متعلقه
    1.25
     onBind
    1.02
    LookAnd
    0.97
    Билгалдахарш
    0.96
     typelib
    0.94
    tagHelperRunner
    0.91
    principalColumn
    0.85
    WithIOException
    0.81
    posedge
    0.80
    sidemargin
    0.80
    Activations Density 2.916%

    No Known Activations