© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105741
    Prev
    Next
    INDEX
    Explanations

    terms related to validation and status checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    uxxxx
    -0.50
    rungsseite
    -0.49
     gezet
    -0.47
    execSQL
    -0.46
    WireFormatLite
    -0.45
     hunne
    -0.43
     dAtA
    -0.43
    ьаж
    -0.42
    __*/
    -0.42
     very
    -0.40
    POSITIVE LOGITS
    istoitu
    0.61
    canActivate
    0.42
    styleType
    0.38
     Disponible
    0.38
    enance
    0.37
    Демографія
    0.37
     Longueur
    0.37
    neté
    0.36
     Trim
    0.36
    Shalom
    0.36
    Activations Density 0.040%

    No Known Activations