© 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. 8-GEMMASCOPE-RES-16K
    6. 10309
    Prev
    Next
    INDEX
    Explanations

    code structure elements like classes, methods, and braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.75
     resourceCulture
    -0.72
     виправивши
    -0.72
     المعيارى
    -0.71
    ISupport
    -0.67
    rawDesc
    -0.67
     Taktlose
    -0.67
    ReusableCell
    -0.66
     ब्रेकडाउन
    -0.66
     useAppContext
    -0.65
    POSITIVE LOGITS
    anovich
    0.51
    bs
    0.42
     Choice
    0.42
    nons
    0.41
     morte
    0.41
    Choice
    0.41
    ImageContext
    0.40
     piac
    0.40
     dell
    0.40
    CHOICE
    0.39
    Activations Density 0.027%

    No Known Activations