© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9861
    Prev
    Next
    INDEX
    Explanations

    references to user interface components and elements related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    choly
    -0.61
     collar
    -0.60
     lode
    -0.59
    chua
    -0.58
    ModelBuilder
    -0.57
    améli
    -0.56
    fromCharCode
    -0.56
    CIAS
    -0.55
    collar
    -0.55
     townships
    -0.55
    POSITIVE LOGITS
     ModelExpression
    0.73
    ftagPool
    0.72
    Temp
    0.67
     EconPapers
    0.66
    bootstrapcdn
    0.66
    saraba
    0.66
    +#+#
    0.65
    ValueStyle
    0.64
     Roskov
    0.63
    tagext
    0.63
    Activations Density 0.026%

    No Known Activations