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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 1939
    Prev
    Next
    INDEX
    Explanations

    marker tokens or special characters indicating the structure of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -1.15
    ValueStyle
    -1.06
    IntoConstraints
    -1.04
    AndEndTag
    -1.01
     esternos
    -0.99
    contentLoaded
    -0.98
    InitVars
    -0.97
    ImageContext
    -0.96
    WireFormatLite
    -0.96
    TintMode
    -0.94
    POSITIVE LOGITS
    멧
    0.42
     cantora
    0.42
     will
    0.39
    slf
    0.39
    .
    0.39
     order
    0.39
    ,\
    0.37
    je
    0.37
     nagu
    0.37
     risk
    0.37
    Activations Density 0.192%

    No Known Activations