© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10801
    Prev
    Next
    INDEX
    Explanations

    terms related to citizenship, legal status, and processes of recognition

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

    ending in "ization", "fication", "idation", "tion", or "ment"

    np_acts-logits-general · gemini-2.0-flash

    formation, creation, optimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.57
    RTHOOK
    -0.54
    expandindo
    -0.51
    msgTypes
    -0.49
    ⟬
    -0.47
     الوا
    -0.47
    zungs
    -0.47
     planète
    -0.47
    FlatAppearance
    -0.46
    testens
    -0.44
    POSITIVE LOGITS
     utilisation
    0.56
     identification
    0.54
    ificación
    0.52
    ficación
    0.51
     preservation
    0.50
     utilization
    0.50
    capsulation
    0.49
    entification
    0.49
     detection
    0.49
    idation
    0.49
    Activations Density 2.104%

    No Known Activations