© 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. 15973
    Prev
    Next
    INDEX
    Explanations

    references to a particular individual and their related legal or medical context

    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
     specchio
    -0.97
     nakalista
    -0.92
    ing
    -0.88
    ]--;
    -0.87
    hept
    -0.87
    دانشنامهٔ
    -0.86
     Blond
    -0.86
    kloped
    -0.85
     Chwiliwch
    -0.85
    ỡng
    -0.85
    POSITIVE LOGITS
    ional
    0.81
    ogeneous
    0.81
     Crosby
    0.80
    Susie
    0.77
    ilies
    0.74
     Susie
    0.73
    Ses
    0.73
    CRIP
    0.72
     Ques
    0.72
     mö
    0.72
    Activations Density 2.044%

    No Known Activations