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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6121
    Prev
    Next
    INDEX
    Explanations

    specific programming keywords and definitions typically associated with defining variables and parameters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archiviato
    -0.57
    DockStyle
    -0.56
    routeProvider
    -0.53
    UserScript
    -0.50
    ftagPool
    -0.49
     Administrativna
    -0.48
     consultato
    -0.47
    exitRule
    -0.46
    astéroïdes
    -0.46
    HostException
    -0.46
    POSITIVE LOGITS
    WithIOException
    0.44
    standen
    0.42
    ACHUSET
    0.41
     Fran
    0.39
    intan
    0.36
    Were
    0.36
    inh
    0.36
    USI
    0.36
    ierre
    0.36
     Rhi
    0.36
    Activations Density 1.002%

    No Known Activations