© 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. 75621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating satisfaction of requirements or conditions

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

    conditions met or violated

    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
    énario
    -0.46
    :✨
    -0.43
    autaire
    -0.43
    oudoune
    -0.43
     accountants
    -0.43
    occuper
    -0.42
    othelioma
    -0.41
     Etik
    -0.40
     Gog
    -0.39
    Figli
    -0.39
    POSITIVE LOGITS
     kasarigan
    0.62
     resourceCulture
    0.57
    WaitGroup
    0.50
    Aktualisiert
    0.50
     estekak
    0.44
    enumii
    0.42
     ContentValues
    0.41
    synthesize
    0.41
    ResponseEntity
    0.40
     by
    0.40
    Activations Density 0.070%

    No Known Activations