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. 18-GEMMASCOPE-RES-16K
    6. 14409
    Prev
    Next
    INDEX
    Explanations

    references to American history and contributions in the context of technology and patents

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

    following "history of" or "early"

    np_acts-logits-general · gemini-2.0-flash

    history and historical events

    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
    Hozzáférés
    -0.71
    Rè
    -0.69
    AlterField
    -0.62
    providedIn
    -0.61
     Roskov
    -0.60
     prochaines
    -0.58
    CrossRef
    -0.57
     propOrder
    -0.57
    ashvili
    -0.56
    cellona
    -0.56
    POSITIVE LOGITS
     history
    0.94
     early
    0.82
     evolution
    0.81
    history
    0.78
    Early
    0.77
    early
    0.77
     Early
    0.76
    EARLY
    0.75
     timeline
    0.66
    History
    0.66
    Activations Density 0.368%

    No Known Activations