© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 64290
    Prev
    Next
    INDEX
    Explanations

    references to specific data, statistics, or results within a research or scientific context

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

    exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    だけでなく
    -0.62
     aswell
    -0.56
    Życiorys
    -0.55
    不仅
    -0.50
    だけではなく
    -0.49
     sambil
    -0.48
     sekaligus
    -0.47
    ContentAsync
    -0.47
    ynchronously
    -0.46
     cũng
    -0.46
    POSITIVE LOGITS
     exceptions
    0.89
    例外
    0.82
     exception
    0.81
     Ausnahme
    0.73
    だけは
    0.72
     Exceptions
    0.72
     excepción
    0.71
     excepted
    0.68
    exceptions
    0.67
    を除
    0.67
    Activations Density 0.067%

    No Known Activations