© 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. 31-GEMMASCOPE-RES-16K
    11. 15361
    Prev
    Next
    INDEX
    Explanations

    references to health-related conditions and changes in behavior

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

    text related to unusual or unexpected situations, often involving legal, medical, or social contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    words that express something being unusual or surprising, often used in comparative contexts or when describing unexpected situations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.50
     kasarigan
    -0.49
    stdc
    -0.48
    MessageTagHelper
    -0.47
    ScopeManager
    -0.47
    enterOuterAlt
    -0.47
    numerusform
    -0.46
    GeoNames
    -0.46
    Portail
    -0.45
     שוליים
    -0.45
    POSITIVE LOGITS
     normally
    3.27
    normally
    2.92
     Normally
    2.75
    Normally
    2.75
     ordinarily
    2.59
     normalmente
    2.56
     usually
    2.55
     usual
    2.50
     normalerweise
    2.45
    Usually
    2.38
    Activations Density 1.183%

    No Known Activations