© 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. 105551
    Prev
    Next
    INDEX
    Explanations

    specific structured data formats or representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     betweenstory
    -0.51
    IVEREF
    -0.50
    RegressionTest
    -0.49
    結果は
    -0.49
     adesivos
    -0.42
     [],
    -0.42
    AuthContext
    -0.42
     CONCLUSIONS
    -0.42
     onData
    -0.42
    GTCX
    -0.41
    POSITIVE LOGITS
     مشين
    0.53
    AndEndTag
    0.47
    httphttps
    0.45
    Javadoc
    0.45
     defaultstate
    0.45
     оригіналу
    0.42
    checkmark
    0.41
     ECT
    0.41
    hline
    0.39
    tip
    0.39
    Activations Density 0.007%

    No Known Activations