© 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. 91316
    Prev
    Next
    INDEX
    Explanations

    colons and similar punctuation used in programming syntax

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

    C++ syntax after user turn

    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
     embarazada
    -0.56
     almohada
    -0.44
     arquitecto
    -0.39
     BitmapFactory
    -0.38
     endfor
    -0.37
     signos
    -0.37
     flecha
    -0.36
     HttpNotFound
    -0.36
    zuführen
    -0.36
    omiast
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.64
    脚注の使い方
    0.59
    }))
    0.58
    :]:
    0.56
     kasarigan
    0.56
    {?>
    0.54
     Nina
    0.54
    </caption>
    0.53
    ')))
    0.53
    Autoritní
    0.53
    Activations Density 0.004%

    No Known Activations