© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10012
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to graphs and structures in mathematical contexts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Jefus
    -1.63
     itſelf
    -1.55
     themſelves
    -1.54
     myſelf
    -1.46
     Efq
    -1.46
     raiſ
    -1.44
     pleaſure
    -1.42
     ſever
    -1.40
     Diſ
    -1.39
     houſe
    -1.37
    POSITIVE LOGITS
     [
    0.86
     (
    0.80
    …
    0.79
     ‘
    0.77
    (
    0.73
     her
    0.72
     our
    0.71
     my
    0.68
     an
    0.68
     a
    0.67
    Activations Density 0.214%

    No Known Activations