© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9917
    Prev
    Next
    INDEX
    Explanations

    discussions about renewal and continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.88
    StructEnd
    -0.70
     FontWeight
    -0.70
    cherichia
    -0.67
    SourceChecksum
    -0.65
    ANTLR
    -0.64
    GraphicsUnit
    -0.64
     referrerpolicy
    -0.63
    libft
    -0.62
     bParam
    -0.61
    POSITIVE LOGITS
    ITHER
    0.80
    dientemente
    0.78
     Regardless
    0.77
    regardless
    0.73
    odynamics
    0.71
    دانشنامهٔ
    0.69
    Regardless
    0.69
     renew
    0.68
     combined
    0.68
     regardless
    0.67
    Activations Density 0.078%

    No Known Activations