© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11763
    Prev
    Next
    INDEX
    Explanations

    fragments of code or programming constructs related to defining and managing grid layouts and UI controls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     THEN
    -0.66
     continuant
    -0.65
     NUKAT
    -0.63
     Tuff
    -0.62
     ALSO
    -0.61
     autorytatywna
    -0.60
    AND
    -0.58
     VERY
    -0.58
     ALWAYS
    -0.57
    NOT
    -0.57
    POSITIVE LOGITS
     tanong
    0.56
    ⁡
    0.54
     ourselves
    0.50
     yourself
    0.49
     another
    0.49
     celle
    0.48
     maybe
    0.47
     anyone
    0.47
     meanwhile
    0.47
     again
    0.47
    Activations Density 0.262%

    No Known Activations