© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2599
    Prev
    Next
    INDEX
    Explanations

    references to previously mentioned concepts or entities in the text

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

    references to previously mentioned content using phrases like "as mentioned above" or "described above".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?,
    -0.43
    iquest
    -0.39
    windowFixed
    -0.39
    !*\
    -0.36
    исленность
    -0.35
    Dabei
    -0.35
    Biografía
    -0.35
    TestTools
    -0.35
    AccessorType
    -0.35
     ModelExpression
    -0.35
    POSITIVE LOGITS
     above
    2.97
    above
    2.58
     aforementioned
    2.31
    Above
    2.28
     Above
    2.23
     mentioned
    2.20
     acima
    2.17
     ABOVE
    2.03
    上述
    1.98
     aforesaid
    1.95
    Activations Density 1.833%

    No Known Activations