© 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. 126676
    Prev
    Next
    INDEX
    Explanations

    HTML template elements related to status messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     kasarigan
    -0.57
    ########.
    -0.57
    IntoConstraints
    -0.56
     怎样
    -0.51
     AssemblyCulture
    -0.50
     utafitiHapana
    -0.47
    __":
    
    -0.46
     sapon
    -0.46
     UIFont
    -0.45
    onedDateTime
    -0.43
    POSITIVE LOGITS
     aberta
    0.47
     Tasche
    0.46
    wußt
    0.42
    ísimo
    0.41
     Ausrüstung
    0.40
     époux
    0.39
     temen
    0.39
     tuyau
    0.39
     morada
    0.38
    fjspx
    0.38
    Activations Density 0.003%

    No Known Activations