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. 13-GEMMASCOPE-RES-16K
    6. 6659
    Prev
    Next
    INDEX
    Explanations

    terms related to genetics and degeneracy in biological contexts

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SPATH
    -0.79
     griega
    -0.69
     nicio
    -0.67
    klä
    -0.64
     sockaddr
    -0.63
     Chernobyl
    -0.63
     tardi
    -0.61
     Alcott
    -0.61
     grecque
    -0.60
     intonation
    -0.60
    POSITIVE LOGITS
    GENER
    1.43
     Generates
    1.37
     generators
    1.33
     Generation
    1.33
     GENER
    1.30
     generator
    1.29
     generation
    1.29
     Generated
    1.28
     Generator
    1.28
     GENERATION
    1.22
    Activations Density 0.143%

    No Known Activations