© 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. 20-GEMMASCOPE-RES-131K
    11. 73696
    Prev
    Next
    INDEX
    Explanations

    coding constructs related to programming structure and layout

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

    left, right, top, bottom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.57
     насељу
    -0.56
    transQ
    -0.54
     TestBed
    -0.47
    antMatchers
    -0.44
     redemption
    -0.43
     समीक्षाएं
    -0.43
     uParam
    -0.43
    لينكات
    -0.43
    TypedDataSet
    -0.42
    POSITIVE LOGITS
     esquerda
    0.46
     Lokales
    0.44
     Porém
    0.43
     edge
    0.41
     corners
    0.40
    gerakan
    0.40
    midler
    0.39
     left
    0.39
    edge
    0.38
    esterno
    0.38
    Activations Density 0.028%

    No Known Activations