Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2425
    Prev
    Next
    INDEX
    Explanations

    references to mathematical proofs and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.81
    findpost
    -0.78
     CreateTagHelper
    -0.78
    Jeografia
    -0.72
     Roskov
    -0.71
    addCriterion
    -0.71
    Tikang
    -0.70
    出版年
    -0.67
    awtextra
    -0.67
    WriteTagHelper
    -0.64
    POSITIVE LOGITS
    Remark
    0.66
    Definition
    0.58
     Remark
    0.57
    CppCodeGen
    0.53
    remark
    0.53
    헌
    0.50
     erinnern
    0.48
     notion
    0.47
     Remarks
    0.46
    Proof
    0.46
    Activations Density 0.600%

    No Known Activations