© 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. 59020
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate the end of statements or sections

    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
    UserScript
    -0.57
    ResponseWriter
    -0.49
     wikipagina
    -0.48
     Wikiseite
    -0.48
    GEBURTSDATUM
    -0.47
     okuyayım
    -0.45
    .*")]
    -0.44
    verwijspagina
    -0.42
     Préférences
    -0.42
    TypedDataSet
    -0.42
    POSITIVE LOGITS
    fjspx
    0.56
    FieldBuilder
    0.54
    AccessorTable
    0.51
    contentLoaded
    0.50
     informée
    0.47
    ſelves
    0.47
    AddTagHelper
    0.46
     ſte
    0.44
    WithIOException
    0.41
    fau
    0.41
    Activations Density 0.000%

    No Known Activations