© 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. 108011
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly those of individuals and organizations

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

    people's names

    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
     typelib
    -0.50
    Jereo
    -0.50
    ValueStyle
    -0.46
    KommentareTeilen
    -0.45
    Välislingid
    -0.44
    MessageTagHelper
    -0.44
     Meilleures
    -0.44
     yyr
    -0.43
    BeginInit
    -0.43
     myſelf
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.50
    rapeau
    0.41
    Espèce
    0.38
    ruptedException
    0.38
     constitucional
    0.37
    IVEREF
    0.33
    PMailer
    0.33
     näky
    0.32
     keterangan
    0.32
     gustaría
    0.32
    Activations Density 0.052%

    No Known Activations