© 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. 17-GEMMASCOPE-RES-16K
    6. 12584
    Prev
    Next
    INDEX
    Explanations

    references to publications and conference proceedings in mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.47
     than
    -0.43
     ne
    -0.43
    uschen
    -0.42
     (
    -0.41
    go
    -0.40
    Normdaten
    -0.40
    媒體
    -0.39
    strom
    -0.39
    wikipedia
    -0.39
    POSITIVE LOGITS
     series
    1.90
     Series
    1.72
    series
    1.72
     SERIES
    1.65
    Series
    1.62
     série
    1.37
    SERIES
    1.36
     serie
    1.30
    Série
    1.26
     séries
    1.25
    Activations Density 0.244%

    No Known Activations