© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15870
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries and medical evaluations

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

    medical or physical injury terms.

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

    sports injury descriptions, particularly specific body parts and injury types.

    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
     diseases
    -0.42
     Fä
    -0.42
    RenderAtEndOf
    -0.41
    krankungen
    -0.40
     cuerpos
    -0.39
     samarbeid
    -0.39
     Krankheiten
    -0.38
    carteles
    -0.38
    Vidite
    -0.38
     řešení
    -0.38
    POSITIVE LOGITS
     undisclosed
    0.56
     hamstring
    0.53
    ichord
    0.52
    ScopeManager
    0.51
     ankle
    0.51
    sterious
    0.50
    alleye
    0.49
     synthesizer
    0.49
     OnTrigger
    0.49
     المعيارى
    0.49
    Activations Density 0.270%

    No Known Activations