© 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. 101093
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and organization across various fields

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

    types and categories

    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
    houd
    -0.47
     wiper
    -0.42
    tifact
    -0.41
     tick
    -0.39
     Material
    -0.39
     dig
    -0.39
     Mania
    -0.39
    racene
    -0.38
     aller
    -0.38
     bagel
    -0.38
    POSITIVE LOGITS
     respectively
    0.59
     respectivamente
    0.58
    respectively
    0.57
    ViewFeatures
    0.57
     båda
    0.53
     behulp
    0.53
     mijne
    0.52
     hindurch
    0.52
     rispet
    0.49
    IntoConstraints
    0.49
    Activations Density 0.060%

    No Known Activations