© 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. 24-GEMMASCOPE-RES-16K
    11. 632
    Prev
    Next
    INDEX
    Explanations

    references to legal principles and judicial decisions

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

    U.S. Supreme Court cases and citations

    np_acts-logits-general · gemini-2.0-flash

    U.S. Supreme Court cases

    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
    EndGlobalSection
    -0.52
     Autorisations
    -0.46
     organiser
    -0.45
    pinch
    -0.45
    zards
    -0.43
    Rhestr
    -0.42
    Proses
    -0.42
     aéro
    -0.41
     pride
    -0.40
    chaleco
    -0.40
    POSITIVE LOGITS
     CURIAM
    0.69
     justices
    0.56
     Supreme
    0.55
     Justices
    0.53
    verifyException
    0.51
    mergeFrom
    0.50
     InputDecoration
    0.49
     surla
    0.49
    supreme
    0.47
    Supreme
    0.47
    Activations Density 1.981%

    No Known Activations