© 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. 7688
    Prev
    Next
    INDEX
    Explanations

    references to hexadecimal and decimal numerical representations

    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
     mAdapter
    -0.94
     endregion
    -0.92
     estekak
    -0.88
     orologio
    -0.82
     lievito
    -0.82
    RetentionPolicy
    -0.82
     ApiService
    -0.82
     ModelRenderer
    -0.80
    TiO
    -0.80
     papilla
    -0.79
    POSITIVE LOGITS
     hex
    1.24
    hex
    1.21
    Hex
    1.16
     Hex
    1.11
     HEX
    1.06
    HEX
    0.97
     ench
    0.78
     gal
    0.76
     fra
    0.74
    av
    0.72
    Activations Density 0.210%

    No Known Activations