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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 12084
    Prev
    Next
    INDEX
    Explanations

    instances of document structure or formatting tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.97
     myſelf
    -0.97
    tvguidetime
    -0.89
    TagMode
    -0.85
     fevere
    -0.84
     aDecoder
    -0.81
    expandindo
    -0.80
    imetsu
    -0.79
     Jefus
    -0.78
     Efq
    -0.78
    POSITIVE LOGITS
     and
    0.62
     The
    0.56
     if
    0.50
     also
    0.46
     And
    0.45
     is
    0.44
     &
    0.44
    .
    0.43
     a
    0.43
     …
    0.42
    Activations Density 0.007%

    No Known Activations