Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9021
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure elements and related commands

    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
    (
    -0.54
    ?
    -0.50
     j
    -0.49
     !(
    -0.48
     „
    -0.48
    //
    -0.47
    ..(
    -0.47
     lo
    -0.46
    -
    -0.45
    rade
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.84
     فريبيس
    0.78
     %,
    0.75
     kasarigan
    0.75
     виправивши
    0.74
     estekak
    0.73
    balleur
    0.71
    FormTagHelper
    0.70
     \%
    0.69
     ligiloj
    0.68
    Activations Density 0.233%

    No Known Activations