© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 12473
    Prev
    Next
    INDEX
    Explanations

    terms related to collectors and collectible items

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

    collecting and collectors

    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
     estekak
    -0.64
    PreExecute
    -0.58
     NUKAT
    -0.57
    SourceChecksum
    -0.54
    Aholisi
    -0.54
    acamole
    -0.53
     <<<<<<<<<<<<<<
    -0.52
     חיצוניים
    -0.52
     lateinit
    -0.52
    tamol
    -0.50
    POSITIVE LOGITS
     coleccion
    0.74
     collectors
    0.67
     collector
    0.64
     collectible
    0.60
     coleção
    0.59
     colección
    0.59
     collections
    0.59
    收藏
    0.57
     collectibles
    0.56
     colecciones
    0.56
    Activations Density 0.007%

    No Known Activations