© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14329
    Prev
    Next
    INDEX
    Explanations

    elements related to SUV features and specifications

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

    Off-road vehicles and driving

    np_acts-logits-general · gemini-2.0-flash

    off-road vehicles, terrain, clearance

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Schöne
    -0.36
     lägen
    -0.35
    massen
    -0.34
     Palais
    -0.33
     Music
    -0.32
     rues
    -0.32
    PackageInfo
    -0.31
     Ballet
    -0.31
     SqlConnection
    -0.31
     casino
    -0.30
    POSITIVE LOGITS
     wilderness
    0.76
     Wilderness
    0.72
     expedition
    0.72
     فريبيس
    0.71
     expeditions
    0.69
     Rugged
    0.68
     rugged
    0.67
     jeep
    0.66
     adventurer
    0.66
     campfire
    0.65
    Activations Density 0.400%

    No Known Activations