© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 4699
    Prev
    Next
    INDEX
    Explanations

    historical references and discussions related to treaties and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielles
    -0.83
     Kontext
    -0.81
     dépla
    -0.75
     culturelles
    -0.72
     étoit
    -0.69
     contextos
    -0.69
     attendu
    -0.69
     étoient
    -0.68
     africains
    -0.68
     pauvres
    -0.65
    POSITIVE LOGITS
    TagMode
    0.62
     coö
    0.61
     definite
    0.59
     mengadakan
    0.59
     régime
    0.56
    wußt
    0.56
    nique
    0.55
     phases
    0.55
    DateTimeField
    0.55
    opsida
    0.54
    Activations Density 0.571%

    No Known Activations