© 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. 7-GEMMASCOPE-RES-16K
    6. 4350
    Prev
    Next
    INDEX
    Explanations

    references to programming elements and configurations, particularly in Maven or HTML/CSS contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refusé
    -0.64
    imab
    -0.60
    islation
    -0.60
    exels
    -0.56
     humide
    -0.55
     IntPtr
    -0.55
    tament
    -0.55
     NDEBUG
    -0.54
    vetica
    -0.54
    ^(@)
    -0.53
    POSITIVE LOGITS
     ModelExpression
    1.06
    Hochspringen
    0.96
     nakalista
    0.81
    出版年
    0.81
    ValueStyle
    0.79
    CppMethod
    0.74
    getItemId
    0.72
     CallOverrides
    0.71
     nahilalakip
    0.70
    Tikang
    0.69
    Activations Density 0.026%

    No Known Activations