© 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. 46943
    Prev
    Next
    INDEX
    Explanations

    references to people, their actions, or statuses within various contexts

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

    therefore to

    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
     gab
    -0.34
    Derbyniad
    -0.33
     pap
    -0.31
     bris
    -0.30
     remember
    -0.30
     pre
    -0.30
     fint
    -0.30
    호
    -0.30
    EDEFAULT
    -0.28
     dynamic
    -0.28
    POSITIVE LOGITS
    ésult
    0.61
     therefore
    0.61
    idemiology
    0.60
     GenerationType
    0.60
    ContentAsync
    0.60
    ſehen
    0.58
     zoude
    0.57
     terpaksa
    0.57
     חיצוניים
    0.57
     actionPerformed
    0.56
    Activations Density 0.035%

    No Known Activations