Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10271
    Prev
    Next
    INDEX
    Explanations

    references to injuries and medical conditions resulting from violent incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.63
     tartalomajánló
    -0.60
    WebElementEntity
    -0.55
    bulaire
    -0.52
     Normdatei
    -0.52
     "..\..\
    -0.51
     "..\..\..\
    -0.51
    fjspx
    -0.51
    SharedCtor
    -0.46
    WithIOException
    -0.46
    POSITIVE LOGITS
     wounds
    1.87
     injuries
    1.72
     Wounds
    1.58
     wound
    1.55
     injury
    1.55
     wounded
    1.54
     wounding
    1.50
     Injuries
    1.45
    wound
    1.43
     Wound
    1.41
    Activations Density 0.382%

    No Known Activations