© 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. 10251
    Prev
    Next
    INDEX
    Explanations

    references to legal case identification and citations

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

    Followed by "Id."

    np_acts-logits-general · gemini-2.0-flash

    Id. citation

    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
     تضيفلها
    -0.68
     ProtoMessage
    -0.67
     <>",
    -0.61
    المناصب
    -0.54
     ब्रेकडाउन
    -0.52
    tagHelperRunner
    -0.51
    səhifə
    -0.50
    webElementXpaths
    -0.50
    AutoModerator
    -0.48
    devamını
    -0.47
    POSITIVE LOGITS
    OrNil
    0.38
     Bill
    0.38
     CP
    0.38
     NIS
    0.35
     weakly
    0.34
    既
    0.34
    RLock
    0.33
     Crack
    0.33
     contacts
    0.33
    cp
    0.33
    Activations Density 0.511%

    No Known Activations