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. 14102
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and measurements in a scientific context

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

    Floating point numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and percentages

    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
    aarrggbb
    -0.62
    rovnik
    -0.57
    __]
    -0.55
    ArrowToggle
    -0.54
    jgl
    -0.54
    bní
    -0.54
    XmlRootElement
    -0.53
    MessageOf
    -0.50
     Signalez
    -0.50
     autorytatywna
    -0.49
    POSITIVE LOGITS
    5
    0.74
    ">—
    0.58
    Tikang
    0.52
    Архівовано
    0.50
     Vella
    0.49
    .*")]
    0.46
    parseLong
    0.46
    lägen
    0.45
    Filmografia
    0.45
    setof
    0.44
    Activations Density 0.262%

    No Known Activations