© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41277
    Prev
    Next
    INDEX
    Explanations

    requests or mentions of needs and requirements in a context

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

    items, . , initial, next, confident, sentence, requirements, use, need, see, instantly, consensus

    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
    ⟭
    -0.71
     Administrativna
    -0.65
     HttpNotFound
    -0.61
     nakalista
    -0.58
     Италијани
    -0.56
    RegressionTest
    -0.54
    tibus
    -0.54
    LookAnd
    -0.54
    ImageContext
    -0.54
     kysy
    -0.53
    POSITIVE LOGITS
    featureID
    0.40
    
    0.30
     IV
    0.28
     pin
    0.28
     volte
    0.26
    NECT
    0.26
    ESIS
    0.25
    mejor
    0.25
    apin
    0.24
    istos
    0.24
    Activations Density 0.112%

    No Known Activations