© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 8074
    Prev
    Next
    INDEX
    Explanations

    the presence of the opening of a text or document

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    MemoryWarning
    -0.53
    spooky
    -0.50
    nestjs
    -0.49
    stoffe
    -0.48
    °•
    -0.48
    reel
    -0.47
     klima
    -0.46
    (__('
    -0.46
    λαμβ
    -0.46
    XmlAccessType
    -0.46
    POSITIVE LOGITS
    estacks
    0.64
     متعلقه
    0.63
     صوتيه
    0.61
    GEBURTSDATUM
    0.59
     décid
    0.58
    Spline
    0.52
     unwise
    0.52
    Encyclopædia
    0.50
     vaut
    0.49
     kaynağından
    0.49
    Activations Density 0.030%

    No Known Activations