© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2855
    Prev
    Next
    INDEX
    Explanations

    nested structures or groupings represented by curly braces

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

    Code or math snippets beginning with '{'

    np_acts-logits-general · gemini-2.0-flash

    conditional programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    setVerticalGroup
    -1.03
    majánló
    -0.75
     propOrder
    -0.69
    pecabe
    -0.67
    BeginInit
    -0.67
     Geiſt
    -0.65
    ientras
    -0.65
    SharedDtor
    -0.65
    ंदीखरीदारी
    -0.64
     wireType
    -0.63
    POSITIVE LOGITS
    {
    0.64
    }{*}{
    0.58
    The
    0.53
    |}{
    0.52
    _
    0.46
    <b>
    0.45
    ="
    0.45
    <td>
    0.45
    {'
    0.42
    <strong>
    0.42
    Activations Density 0.069%

    No Known Activations