© 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. 0-GEMMASCOPE-RES-16K
    11. 7874
    Prev
    Next
    INDEX
    Explanations

    references to specific volumes of academic or scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.11
    ^(@)
    -1.09
    DockStyle
    -1.02
     occaf
    -1.01
     photolibrary
    -1.01
    ValueStyle
    -1.00
     Efq
    -0.97
    wiſe
    -0.96
     cauſe
    -0.95
     raiſ
    -0.95
    POSITIVE LOGITS
    zu
    0.72
    RB
    0.61
     der
    0.59
    ↵↵
    0.58
    los
    0.58
    \
    0.58
    rb
    0.58
    level
    0.57
    old
    0.57
     
    0.55
    Activations Density 0.111%

    No Known Activations