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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12998
    Prev
    Next
    INDEX
    Explanations

    repeated numerical values in sequences or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    antMatchers
    -0.69
    WriteAttribute
    -0.66
     للمعارف
    -0.64
     שוליים
    -0.61
    RequestParam
    -0.60
     Tully
    -0.60
    省市镇
    -0.59
     CreateTagHelper
    -0.56
     estekak
    -0.56
     useParams
    -0.56
    POSITIVE LOGITS
    setVerticalGroup
    0.81
    schmidt
    0.74
    )];
    
    0.72
     PyLong
    0.70
    ardless
    0.70
    rungsseite
    0.69
    Captor
    0.68
     }</
    0.66
     cata
    0.66
    LabelTagHelper
    0.66
    Activations Density 0.101%

    No Known Activations