© 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 - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15030
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pack" and its variations, indicating a focus on packing-related terminology

    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
    setHorizontal
    -0.77
     surla
    -0.70
     Chio
    -0.68
    SSO
    -0.67
     Temmuz
    -0.66
    */].
    -0.66
     Jamestown
    -0.65
    Τι
    -0.65
     pert
    -0.65
     Blaine
    -0.64
    POSITIVE LOGITS
     Pack
    2.52
     pack
    2.49
     PACK
    2.44
    pack
    2.43
    Pack
    2.40
     packs
    2.36
     Packs
    2.23
    PACK
    2.23
    packs
    2.08
    Packs
    2.02
    Activations Density 0.041%

    No Known Activations