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. 0-GEMMASCOPE-RES-16K
    6. 307
    Prev
    Next
    INDEX
    Explanations

    terms related to violence and its impact in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duquel
    -0.71
    достатки
    -0.69
    vician
    -0.67
     ainfi
    -0.67
     feroit
    -0.66
    fortunately
    -0.63
    ]--;
    -0.63
     présidenti
    -0.62
    monary
    -0.61
     pauv
    -0.61
    POSITIVE LOGITS
     Violence
    0.68
    Honorable
    0.66
    ine
    0.63
    rr
    0.62
    €
    0.62
    doctype
    0.61
    Violence
    0.60
     يتيمه
    0.60
     violence
    0.59
    PDOException
    0.57
    Activations Density 0.115%

    No Known Activations