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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1779
    Prev
    Next
    INDEX
    Explanations

    specific code structure or syntax from technical documents

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

    Code diffs and technical documents

    np_acts-logits-general · gemini-2.0-flash

    phys. @ or diff

    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
    httphttps
    -0.53
    WebElementEntity
    -0.48
    Tracce
    -0.43
    XmlEnum
    -0.40
    #
    -0.39
    -------------</
    -0.39
    UserScript
    -0.39
    ReusableCell
    -0.35
    Dichloropropane
    -0.35
    Derbyniad
    -0.35
    POSITIVE LOGITS
    PhysRevD
    0.60
    phazard
    0.54
    kespea
    0.47
     endfor
    0.44
    SPJ
    0.44
    illotine
    0.43
     diodes
    0.43
    abetes
    0.43
    kloped
    0.43
     Wikiseite
    0.42
    Activations Density 0.073%

    No Known Activations