© 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. 1-GEMMASCOPE-RES-16K
    6. 13131
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax associated with programming languages, particularly in the context of variable representation and assignment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.69
     fevere
    -0.66
     Shakspeare
    -0.65
     affatto
    -0.63
     ſever
    -0.60
     onore
    -0.58
    SourceChecksum
    -0.57
     Czechoslovak
    -0.56
     turban
    -0.55
     chiare
    -0.55
    POSITIVE LOGITS
     $
    1.38
     £
    0.88
    '=>$
    0.75
     AssemblyCulture
    0.75
    "=>$
    0.74
    ",$
    0.68
     $\
    0.67
    ReusableCell
    0.67
     $\$
    0.66
    ,$
    0.65
    Activations Density 0.107%

    No Known Activations