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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 13204
    Prev
    Next
    INDEX
    Explanations

    incidents related to crime or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.65
     nahilalakip
    -0.60
    EndProject
    -0.55
    utia
    -0.49
     key
    -0.49
     sẵn
    -0.48
    Demografía
    -0.48
     mẽ
    -0.48
    เฉพาะ
    -0.45
    sizePolicy
    -0.45
    POSITIVE LOGITS
     midnight
    0.78
     madrugada
    0.76
     typelib
    0.68
     ночью
    0.67
    midnight
    0.67
     southbound
    0.65
     anoche
    0.64
     nocturnal
    0.64
     betweenstory
    0.64
     tôt
    0.63
    Activations Density 0.146%

    No Known Activations