© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8164
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     Jank
    -0.75
     Kowal
    -0.74
     Kraw
    -0.72
     Bress
    -0.71
     Geller
    -0.70
     Kowalski
    -0.65
     Steff
    -0.63
     Kruse
    -0.61
     Heff
    -0.60
     Gries
    -0.60
    POSITIVE LOGITS
     Jackson
    0.72
     Walker
    0.70
     Parker
    0.69
     Marshall
    0.66
     Allen
    0.65
     Douglas
    0.63
     Grant
    0.63
     Mitchell
    0.63
    Walker
    0.63
     Davis
    0.62
    Activations Density 1.825%

    No Known Activations