© 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. 66296
    Prev
    Next
    INDEX
    Explanations

    actions and expressions of personal sentiments or opinions

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

    did verb phrases

    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
    ViewImports
    -0.52
    noin
    -0.42
     vola
    -0.41
     ferme
    -0.39
    nex
    -0.39
    movi
    -0.39
    Це
    -0.39
    aih
    -0.39
    ọn
    -0.39
     т
    -0.39
    POSITIVE LOGITS
    ではある
    0.61
     however
    0.58
     Allerdings
    0.57
     comunque
    0.56
     cependant
    0.55
     allerdings
    0.55
     però
    0.55
    anmoins
    0.54
     niestety
    0.54
    erdings
    0.53
    Activations Density 0.036%

    No Known Activations