© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6093
    Prev
    Next
    INDEX
    Explanations

    ellipses and punctuation that suggest hesitation or a pause in thought

    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
     myſelf
    -2.16
     itſelf
    -2.15
     doubtnut
    -1.99
     Efq
    -1.99
     iſt
    -1.87
    )");
    
    -1.86
    ^(@)
    -1.84
     Jefus
    -1.82
    ſelf
    -1.77
     faſt
    -1.76
    POSITIVE LOGITS
    …
    1.98
    ..
    1.91
    ...
    1.89
    ….
    1.56
    ....
    1.55
      
    1.48
    —
    1.39
    !
    1.39
    --
    1.35
    ↵
    1.35
    Activations Density 0.464%

    No Known Activations