© 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. 50655
    Prev
    Next
    INDEX
    Explanations

    financial metrics and performance indicators

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

    financial reporting projections

    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
    byen
    -0.31
     الط
    -0.30
    tasche
    -0.30
    flasche
    -0.29
     сто
    -0.29
    sw
    -0.29
    плу
    -0.28
    skin
    -0.28
     ice
    -0.28
     ML
    -0.27
    POSITIVE LOGITS
     المعيارى
    0.83
     Normdatei
    0.78
    ConstraintMaker
    0.73
     Roskov
    0.73
     profits
    0.68
    profits
    0.67
    profit
    0.65
    ésultats
    0.65
    ðsíða
    0.64
     profit
    0.64
    Activations Density 0.041%

    No Known Activations