© 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. 19-GEMMASCOPE-RES-16K
    11. 15536
    Prev
    Next
    INDEX
    Explanations

    references to saving, editing, and managing files or data changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    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
    -0.60
    таратура
    -0.57
    ArgsConstructor
    -0.55
    nestjs
    -0.55
     समीक्षाएं
    -0.54
     tombé
    -0.54
    MENAFN
    -0.54
    ]--;
    -0.53
    aryen
    -0.53
     nakalista
    -0.53
    POSITIVE LOGITS
     save
    1.72
     saving
    1.65
    save
    1.64
     Save
    1.59
    Save
    1.54
     saves
    1.52
     saved
    1.44
     Saving
    1.40
    Saving
    1.36
     SAVE
    1.36
    Activations Density 0.145%

    No Known Activations