© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 671
    Prev
    Next
    INDEX
    Explanations

    specific variable names or data identifiers used in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequences of numeric values or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quantum states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.80
    Rüyada
    -0.78
    tagHelperRunner
    -0.77
    Solución
    -0.72
     WaitForSeconds
    -0.71
    ########.
    -0.70
    FunctionFlags
    -0.69
    GEBURTSDATUM
    -0.68
    sizeCache
    -0.68
     Italijanski
    -0.67
    POSITIVE LOGITS
     Efq
    0.57
    zeitige
    0.51
    //{
    0.50
    ?—
    0.50
     Telex
    0.48
    herst
    0.48
     fowls
    0.45
    .",
    0.44
    kozások
    0.44
    yaitu
    0.44
    Activations Density 0.084%

    No Known Activations