© 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. 75909
    Prev
    Next
    INDEX
    Explanations

    categorical labels or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ulemon
    -0.44
     Afrika
    -0.37
     AspNetCore
    -0.36
    topi
    -0.36
    籽
    -0.35
     
    -0.34
     ethos
    -0.34
     Proben
    -0.34
    sao
    -0.34
    GestureDetector
    -0.34
    POSITIVE LOGITS
    EObject
    1.13
    OGND
    0.87
    EReference
    0.72
    ecore
    0.69
    ObjectContext
    0.68
     nakalista
    0.68
    EDEFAULT
    0.67
    IntoConstraints
    0.65
    ftagPool
    0.63
     Roskov
    0.61
    Activations Density 0.000%

    No Known Activations