© 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. 24085
    Prev
    Next
    INDEX
    Explanations

    various formatting styles indicated by the tokens

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

    style="

    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
    </tr>
    -0.36
      
    -0.35
     따라
    -0.31
    }`).
    -0.30
    ↵
    -0.28
     $\
    -0.27
     </
    -0.27
              
    -0.26
     states
    -0.26
    \
    -0.26
    POSITIVE LOGITS
    uxxxx
    1.00
    ValueStyle
    0.87
    aarrggbb
    0.84
     المعيارى
    0.83
     ब्रेकडाउन
    0.82
     autorytatywna
    0.79
     NSCoder
    0.77
    OGND
    0.77
    脚注の使い方
    0.76
    səhifə
    0.73
    Activations Density 0.034%

    No Known Activations