© 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. 3-GEMMASCOPE-RES-16K
    11. 7055
    Prev
    Next
    INDEX
    Explanations

    terms associated with medicinal and biochemical contexts, including references to specific compounds and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogeneous
    -0.89
    ilies
    -0.76
    Ses
    -0.76
     Ses
    -0.74
    Susie
    -0.74
    ional
    -0.73
    eken
    -0.69
     Crosby
    -0.68
    eman
    -0.67
    Frankie
    -0.66
    POSITIVE LOGITS
    ]--;
    1.01
     specchio
    0.94
    kloped
    0.93
     Blond
    0.93
    Edd
    0.92
    hept
    0.91
     dépens
    0.89
    ECAUSE
    0.89
     Pears
    0.88
     Agust
    0.85
    Activations Density 2.628%

    No Known Activations