© 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. 15-GEMMASCOPE-RES-16K
    6. 1185
    Prev
    Next
    INDEX
    Explanations

    financial figures and expenditures related to budgets and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     golongan
    -0.41
    掌
    -0.38
     quelcon
    -0.37
     pintadas
    -0.34
    dhury
    -0.34
    تف
    -0.34
    noční
    -0.34
    näm
    -0.33
     riego
    -0.33
    mittags
    -0.33
    POSITIVE LOGITS
    RenderAtEndOf
    1.17
    awtextra
    0.90
    setVerticalGroup
    0.85
     ModelExpression
    0.83
     betweenstory
    0.81
    SBATCH
    0.77
    URLException
    0.76
    -£
    0.76
    rawDesc
    0.76
     configureStore
    0.74
    Activations Density 0.369%

    No Known Activations