© 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. 3-GEMMASCOPE-RES-16K
    6. 6907
    Prev
    Next
    INDEX
    Explanations

    terms associated with wounds and wound healing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.51
    posedge
    -0.44
     للاسماء
    -0.44
    nass
    -0.43
    OrNil
    -0.43
    发表于
    -0.43
    ETYPE
    -0.42
     itinéraires
    -0.41
    Lol
    -0.41
    JvmStatic
    -0.40
    POSITIVE LOGITS
     wound
    0.82
     primitive
    0.77
    wound
    0.75
     Wound
    0.73
    primitive
    0.68
     wounds
    0.68
     Primitive
    0.66
    Wound
    0.66
    Primitive
    0.63
     Wounds
    0.60
    Activations Density 1.139%

    No Known Activations