Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53111
    Prev
    Next
    INDEX
    Explanations

    specific sequences or structures in genetic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    GTR sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iſt
    -0.66
     actual
    -0.59
    puter
    -0.59
    acchi
    -0.57
    νι
    -0.57
    æus
    -0.57
    tiary
    -0.57
    ceto
    -0.56
    uſ
    -0.56
    zenberg
    -0.55
    POSITIVE LOGITS
    expandindo
    0.80
     Normdatei
    0.66
     Faso
    0.63
    UAWEI
    0.63
    ⓧ
    0.60
    
    0.59
     समीक्षाओं
    0.57
    
    0.57
     GNA
    0.56
    issauga
    0.56
    Activations Density 0.010%

    No Known Activations