© 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. 3037
    Prev
    Next
    INDEX
    Explanations

    concepts related to sharing knowledge and resources in collaborative contexts

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

    sharing information and knowledge

    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
     surla
    -0.79
    awtextra
    -0.77
    IntoConstraints
    -0.59
    SequentialGroup
    -0.57
     ſtate
    -0.55
    enterOuterAlt
    -0.55
     BoxDecoration
    -0.55
     IBOutlet
    -0.52
    MigrationBuilder
    -0.51
     houſe
    -0.50
    POSITIVE LOGITS
     sharing
    0.62
     compartir
    0.61
     partage
    0.57
     intercambio
    0.54
    sharing
    0.52
     compartido
    0.51
     partagé
    0.51
     compartida
    0.50
     Sharing
    0.49
    Sharing
    0.49
    Activations Density 0.010%

    No Known Activations