Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1945
    Prev
    Next
    INDEX
    Explanations

    end-of-statement syntax in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stre
    -0.46
     Sutton
    -0.45
     dAtA
    -0.44
     plus
    -0.43
     mergeFrom
    -0.42
    ://
    -0.42
    Sinopse
    -0.42
    ,
    -0.41
     and
    -0.41
     any
    -0.40
    POSITIVE LOGITS
     ujednoznacz
    0.69
    //
    0.67
    AutoScaleMode
    0.65
    expandindo
    0.64
    providedIn
    0.63
    NUMX
    0.63
    calaureate
    0.62
    Cyfeiriadau
    0.62
    SharedCtor
    0.62
     Monfieur
    0.62
    Activations Density 0.126%

    No Known Activations