© 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. 80500
    Prev
    Next
    INDEX
    Explanations

    high-frequency, non-alphanumeric symbols and specific numeric values

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

    language identification

    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
    i
    -0.24
     
    -0.23
    Full
    -0.22
    K
    -0.22
    full
    -0.20
    M
    -0.20
    INDA
    -0.20
    Z
    -0.20
    多
    -0.19
     [
    -0.19
    POSITIVE LOGITS
     Administrativna
    1.16
     Infórmanos
    1.00
     nakalista
    0.91
     Италијани
    0.91
    évaluateur
    0.90
    Cyfarwyddwr
    0.86
    NameInMap
    0.85
    rungsseite
    0.85
    oa̍t
    0.84
     Italijanski
    0.84
    Activations Density 0.001%

    No Known Activations