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. 53227
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online resources

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

    urls starting with http or https

    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
     Réponses
    -0.73
    '>{
    -0.70
    CPtr
    -0.68
    withIdentifier
    -0.67
    ModelState
    -0.66
    StoryboardSegue
    -0.65
    PostExecute
    -0.64
    NUMX
    -0.63
    ']],
    -0.63
    ʺ
    -0.63
    POSITIVE LOGITS
    http
    0.95
     http
    0.89
    https
    0.88
    ://
    0.84
     https
    0.81
    www
    0.76
     www
    0.75
    ttps
    0.70
    ttp
    0.64
    href
    0.56
    Activations Density 0.036%

    No Known Activations