© 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. 33-GEMMASCOPE-RES-16K
    11. 819
    Prev
    Next
    INDEX
    Explanations

    multiple levels of nested parentheses and braces in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.66
     noqa
    -0.65
    abestanden
    -0.65
    WillAppear
    -0.64
     ſtate
    -0.62
    Diweddarwch
    -0.57
    AsUp
    -0.56
     createSprite
    -0.56
     commitment
    -0.55
    jsii
    -0.55
    POSITIVE LOGITS
    sterious
    0.42
    ){
    0.36
    --){
    0.35
    schnitt
    0.35
    GETHER
    0.33
    ing
    0.33
    eb
    0.33
    itado
    0.32
    ...}
    0.32
    mannschaft
    0.32
    Activations Density 0.287%

    No Known Activations