© 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. 20979
    Prev
    Next
    INDEX
    Explanations

    sections related to professional achievements and contributions in various fields

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

    publications, discography, goals, film, statistics

    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
    الحياه
    -0.67
    expandindo
    -0.62
     تانيه
    -0.47
    Hozzáférés
    -0.47
    хіво
    -0.45
     Cracks
    -0.45
    elemField
    -0.44
     CreateTagHelper
    -0.42
    autogui
    -0.42
     تكبرها
    -0.42
    POSITIVE LOGITS
    transQ
    0.52
    Filmografia
    0.43
    Filmografie
    0.43
     initComponents
    0.42
    Identyfik
    0.41
     nakalista
    0.40
     published
    0.36
    DispatchToProps
    0.35
    GroupLayout
    0.35
     completed
    0.35
    Activations Density 0.018%

    No Known Activations