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 - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7884
    Prev
    Next
    INDEX
    Explanations

    references to persistent regional terms or identifiers, specifically relating to the "PR" designation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CWE
    -0.92
     InputDecoration
    -0.84
    AddTagHelper
    -0.82
     feroit
    -0.78
    Ծանոթ
    -0.78
     bénévoles
    -0.78
    principalColumn
    -0.75
     extérieures
    -0.74
     blessés
    -0.73
     TestBed
    -0.72
    POSITIVE LOGITS
     PR
    0.69
     Ve
    0.62
    {
    0.57
    '
    0.56
    \]
    0.55
    Tembelea
    0.54
    Ve
    0.53
    <em>
    0.53
    PR
    0.53
    zky
    0.52
    Activations Density 0.409%

    No Known Activations