© 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. 3-GEMMASCOPE-RES-16K
    11. 11335
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs related to function definitions and calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allí
    -0.64
    LLocation
    -0.60
    RTEE
    -0.57
    igshid
    -0.56
     protoimpl
    -0.56
     vnode
    -0.55
     Celui
    -0.55
     ...'
    -0.55
     مشين
    -0.55
     saka
    -0.55
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
    TProtocol
    0.56
     AssemblyVersion
    0.51
    bootstrapcdn
    0.50
     بگذار
    0.49
    preventDefault
    0.48
    $_['
    0.48
    </thead>
    0.48
    发表于
    0.48
    imenti
    0.47
    Activations Density 0.299%

    No Known Activations