© 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. 12588
    Prev
    Next
    INDEX
    Explanations

    legal citations and references in a judicial 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
    СР
    -0.66
    — 
    -0.63
     estekak
    -0.61
    `,
    -0.58
    — 
    -0.56
    Бахар
    -0.56
    cydow
    -0.56
    czegó
    -0.56
    ]){
    -0.55
    AndEndTag
    -0.54
    POSITIVE LOGITS
     fathoms
    0.65
     CommonModule
    0.63
     RouterModule
    0.63
    iprot
    0.59
     Acetate
    0.56
     Coulomb
    0.54
    Hentet
    0.54
    ConstraintMaker
    0.54
    AutoScaleMode
    0.54
     Chwiliwch
    0.53
    Activations Density 0.799%

    No Known Activations