© 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. 9389
    Prev
    Next
    INDEX
    Explanations

    instances of citation and references in documentation

    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
     that
    -2.90
    that
    -2.15
     That
    -2.09
    That
    -2.05
     THAT
    -1.84
    THAT
    -1.74
     those
    -1.66
    那
    -1.64
     thats
    -1.62
    thats
    -1.52
    POSITIVE LOGITS
    this
    0.56
    providedIn
    0.50
     this
    0.49
     această
    0.47
    AutoField
    0.46
     ویکی‌پدیای
    0.45
     본
    0.44
     дан
    0.44
    quante
    0.43
     GenerationType
    0.43
    Activations Density 0.519%

    No Known Activations