© 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 - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6657
    Prev
    Next
    INDEX
    Explanations

    the word "config."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MediatR
    -0.77
    Portail
    -0.74
    GraphicsUnit
    -0.74
    RTEE
    -0.74
     Chaldean
    -0.72
    Portale
    -0.72
    writeFieldEnd
    -0.68
     Majefty
    -0.67
     uſed
    -0.66
    InjectAttribute
    -0.65
    POSITIVE LOGITS
    config
    3.10
     config
    2.05
    Config
    1.61
     Config
    1.23
    CONFIG
    1.21
    setConfig
    1.16
    configs
    1.06
    getConfig
    0.97
    Configs
    0.92
     CONFIG
    0.78
    Activations Density 0.088%

    No Known Activations