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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 12491
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and their syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Starts with an underscore

    np_acts-logits-general · gemini-2.0-flash

    underscore followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    -0.70
    {}'.
    -0.63
    {}".
    -0.62
    HtmlAttribute
    -0.53
    __).
    -0.52
     שוליים
    -0.51
    grà
    -0.50
    AsUp
    -0.49
    /*
    -0.47
    \{\\
    -0.46
    POSITIVE LOGITS
    jspx
    0.92
    Personendaten
    0.74
    =_
    0.67
    localctx
    0.67
    Nonnull
    0.57
    ViewImports
    0.57
    &_
    0.56
    contentLoaded
    0.53
    Abp
    0.53
    ._
    0.53
    Activations Density 0.094%

    No Known Activations