© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38544
    Prev
    Next
    INDEX
    Explanations

    specific formatting or syntax elements, likely related to citations or metadata in academic texts

    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
     BorderRadius
    -0.62
     كومونز
    -0.56
     Tri
    -0.51
    esia
    -0.51
     para
    -0.51
     tri
    -0.50
     por
    -0.49
     bien
    -0.48
    ably
    -0.48
     kom
    -0.48
    POSITIVE LOGITS
     itſelf
    1.09
     poffe
    1.02
     myſelf
    1.00
     fubject
    0.99
     Efq
    0.94
     himſelf
    0.92
     poffible
    0.90
     fhort
    0.90
     defire
    0.90
     purpoſe
    0.89
    Activations Density 0.000%

    No Known Activations