© 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. 23-GEMMASCOPE-RES-16K
    11. 9292
    Prev
    Next
    INDEX
    Explanations

    digits and alphanumeric strings

    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
     ostavi
    -0.53
     olje
    -0.50
    cadi
    -0.46
     jaj
    -0.45
    CC
    -0.45
    )}_{
    -0.45
    НТ
    -0.45
    IBC
    -0.43
    FF
    -0.43
    DF
    -0.43
    POSITIVE LOGITS
    adget
    0.61
    awtextra
    0.57
    ConstraintMaker
    0.57
    styleable
    0.56
     newList
    0.56
    UnusedPrivate
    0.55
    reshold
    0.54
    σθαι
    0.53
    estinian
    0.53
    esterday
    0.53
    Activations Density 0.266%

    No Known Activations