© 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. 106033
    Prev
    Next
    INDEX
    Explanations

    syntax and structure in programming code

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

    code configuration documentation parameter

    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
    parsedMessage
    -0.99
     disambiguazione
    -0.96
     iNdEx
    -0.94
     ujednoznacz
    -0.92
     geweſen
    -0.82
    <unused68>
    -0.82
     パンチラ
    -0.82
    GEBURTSDATUM
    -0.82
    [@BOS@]
    -0.82
    <unused23>
    -0.82
    POSITIVE LOGITS
     Presidencia
    0.28
     toalla
    0.28
     refuer
    0.28
     fortaleza
    0.26
     piden
    0.26
    ."
    0.25
     cláus
    0.24
     obligatorio
    0.24
     tornillos
    0.24
     devront
    0.24
    Activations Density 0.004%

    No Known Activations