© 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 EvalsExportsAPI 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. 3905
    Prev
    Next
    INDEX
    Explanations

    references to events, structures, and classifications

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

    Follows "edition", "no", or "class"

    np_acts-logits-general · gemini-2.0-flash

    edition, class, this, no

    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
    featureID
    -0.75
    IsContent
    -0.67
    <unused17>
    -0.65
    ⟬
    -0.65
    <unused43>
    -0.65
    <unused23>
    -0.64
    <unused68>
    -0.64
    <unused14>
    -0.64
    <pad>
    -0.64
    <unused7>
    -0.64
    POSITIVE LOGITS
    retudo
    0.32
     feltro
    0.31
    proof
    0.31
    cluso
    0.30
     pareil
    0.29
    เช่น
    0.29
    าก็
    0.29
     خاصة
    0.29
    今回も
    0.29
     menyus
    0.28
    Activations Density 0.132%

    No Known Activations