© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105562
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical mappings and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical terminology referring to components or concepts that connect or bridge between different systems, structures, or mathematical objects.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.46
    RegistryLite
    -0.46
    帖最后由
    -0.45
    ByVersion
    -0.45
    MessageState
    -0.45
    trav
    -0.45
    PutPixel
    -0.44
    ࿐
    -0.42
    ApiModel
    -0.41
    epam
    -0.40
    POSITIVE LOGITS
    httphttps
    0.50
    tranno
    0.46
    TargetException
    0.43
    DrawerToggle
    0.43
     conversion
    0.42
     converts
    0.42
     måte
    0.42
     Conversion
    0.40
     converting
    0.40
     Converts
    0.40
    Activations Density 0.187%

    No Known Activations