© 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. 13-GEMMASCOPE-RES-65K
    11. 56415
    Prev
    Next
    INDEX
    Explanations

    frequency of certain symbols or special characters in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.82
     onCreateView
    -0.77
    DockStyle
    -0.73
     ModelRenderer
    -0.72
     defaultstate
    -0.68
     насељу
    -0.68
     ſtate
    -0.66
     perfons
    -0.66
     erythrocytes
    -0.66
     uſe
    -0.65
    POSITIVE LOGITS
     etc
    0.56
    transQ
    0.50
    MemoryWarning
    0.50
     post
    0.47
    zeera
    0.45
     round
    0.44
    ofire
    0.44
     M
    0.43
     “
    0.42
     plus
    0.42
    Activations Density 0.026%

    No Known Activations