© 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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2670
    Prev
    Next
    INDEX
    Explanations

    elements related to coding, specifically paths and variable assignments in scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.38
    complexType
    -0.33
     Ei
    -0.31
    Portale
    -0.31
    ScopeManager
    -0.30
    (!__
    -0.30
     Deep
    -0.29
     ска
    -0.29
     corps
    -0.29
     typ
    -0.29
    POSITIVE LOGITS
    
    0.76
    Diweddarwch
    0.59
     mariée
    0.57
    parsedMessage
    0.56
    SharedCtor
    0.54
     Meinung
    0.54
    AccessorTable
    0.53
    graphicx
    0.53
    ágenes
    0.52
    omitempty
    0.52
    Activations Density 0.165%

    No Known Activations