© 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. 896
    Prev
    Next
    INDEX
    Explanations

    references to wheels and their related concepts in various contexts

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

    "wheel" or "wheels"

    np_acts-logits-general · gemini-2.0-flash

    wheel of the year or wheel of something

    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
    chalten
    -0.47
    PLICATE
    -0.47
    brücken
    -0.47
    zok
    -0.46
    sol
    -0.46
     Langer
    -0.46
     članak
    -0.45
     longer
    -0.45
    ತಿ
    -0.44
    ряда
    -0.44
    POSITIVE LOGITS
     wheel
    0.82
     Wheel
    0.79
     wheels
    0.79
    Wheel
    0.75
    Wheels
    0.75
    barrow
    0.73
    WHE
    0.68
     Wheels
    0.68
    wheel
    0.68
     WHEEL
    0.66
    Activations Density 0.107%

    No Known Activations