Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 85373
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting properties in code or style definitions

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

    color assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.80
    expandindo
    -0.76
     HasFactory
    -0.74
     endforeach
    -0.69
     ſua
    -0.69
    UserScript
    -0.68
    ſſung
    -0.67
    MarshalTo
    -0.67
    <unused8>
    -0.66
    <unused28>
    -0.66
    POSITIVE LOGITS
     color
    1.28
     Color
    1.13
     colour
    1.10
    Color
    1.09
    color
    1.05
     COLOR
    1.02
     couleur
    0.99
     colors
    0.98
    COLOR
    0.98
    Colour
    0.95
    Activations Density 0.005%

    No Known Activations