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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8139
    Prev
    Next
    INDEX
    Explanations

    angle brackets and their placements in template definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.50
    IntoConstraints
    -0.49
    LEncoder
    -0.49
    ,$_
    -0.47
     שוליים
    -0.46
    gridy
    -0.45
     cauſe
    -0.45
     majority
    -0.44
    PreExecute
    -0.44
     مشين
    -0.42
    POSITIVE LOGITS
    <
    1.03
    <[
    0.78
    ::<
    0.72
    <{
    0.69
    langle
    0.65
    <(
    0.62
    \<
    0.62
    ⟨
    0.60
    《
    0.60
    _<
    0.59
    Activations Density 0.063%

    No Known Activations