© 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. 23-GEMMASCOPE-RES-16K
    6. 3996
    Prev
    Next
    INDEX
    Explanations

    semicolons and parentheses in code snippets

    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
    Tradu
    -0.70
     ་་
    -0.61
     吗
    -0.56
    ValueGeneration
    -0.54
     Houſe
    -0.54
     )
    -0.52
     canlynol
    -0.52
     doubtnut
    -0.52
    wiſe
    -0.51
     Explora
    -0.51
    POSITIVE LOGITS
    ÉN
    0.60
    ÁG
    0.60
     z
    0.60
    олові
    0.59
     //
    0.58
     str
    0.57
    UCION
    0.56
     continue
    0.55
    athione
    0.55
    വല
    0.55
    Activations Density 0.206%

    No Known Activations