© 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. 19-GEMMASCOPE-RES-16K
    11. 3330
    Prev
    Next
    INDEX
    Explanations

    formal statements or press releases related to public officials and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ناك
    -0.51
    jspx
    -0.50
    ticed
    -0.45
    ecore
    -0.45
    нала
    -0.45
     Altri
    -0.45
     quæ
    -0.45
     /\.(
    -0.44
     convinced
    -0.44
    vinced
    -0.44
    POSITIVE LOGITS
     statement
    2.02
     spokesperson
    1.81
     spokesman
    1.80
    statement
    1.71
     spokeswoman
    1.69
     Statement
    1.68
     Spokes
    1.61
    Statement
    1.58
     STATEMENT
    1.56
     statements
    1.52
    Activations Density 0.160%

    No Known Activations