© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2897
    Prev
    Next
    INDEX
    Explanations

    references to Volkswagen car models and their specifications

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

    Comes after a number or period

    np_acts-logits-general · gemini-2.0-flash

    car models and engines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    substack
    -0.55
    CellValue
    -0.54
     Motos
    -0.53
     useAppContext
    -0.52
    makeText
    -0.50
     bicarbon
    -0.49
     getItemId
    -0.49
     désolés
    -0.45
     Jeune
    -0.45
     Uniti
    -0.45
    POSITIVE LOGITS
     Sloane
    0.59
    لينكات
    0.58
     '/':
    0.55
    amilya
    0.54
    }(),
    0.54
    RegistryLite
    0.54
    stang
    0.53
    wyk
    0.53
    shtml
    0.53
     vidro
    0.53
    Activations Density 0.113%

    No Known Activations