© 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. 43144
    Prev
    Next
    INDEX
    Explanations

    phrases indicating starting points or beginnings of discussions or processes

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

    starting things

    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
     Jesucristo
    -0.44
     chaqueta
    -0.35
    numerusform
    -0.34
    MUX
    -0.33
     confirmer
    -0.31
    miec
    -0.31
    Significado
    -0.30
    HasColumnType
    -0.29
     Gies
    -0.29
     fun
    -0.29
    POSITIVE LOGITS
     comuniques
    0.69
     pinulongan
    0.67
    Personendaten
    0.65
     Italijanski
    0.64
     utafitiHapana
    0.63
     starters
    0.62
    START
    0.61
     starts
    0.61
    starts
    0.61
    starter
    0.61
    Activations Density 0.018%

    No Known Activations