Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8380
    Prev
    Next
    INDEX
    Explanations

    terms associated with irrationality or craziness

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

    the word "crazy"

    np_acts-logits-general · gemini-2.0-flash

    absurd or extreme situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.66
    meneu
    -0.64
    Datuak
    -0.64
    ChildIndex
    -0.62
     समीक्षक
    -0.61
    multicolumn
    -0.60
    rxjs
    -0.57
     AssemblyProduct
    -0.57
    cotch
    -0.57
    upuncture
    -0.55
    POSITIVE LOGITS
     insane
    0.71
     crazy
    0.69
     monstre
    0.68
     behavior
    0.67
     nonsense
    0.63
     poffible
    0.62
    posterous
    0.61
     behaviour
    0.61
    insane
    0.61
    Crazy
    0.61
    Activations Density 0.239%

    No Known Activations