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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 11678
    Prev
    Next
    INDEX
    Explanations

    phrases related to acts of violence or physical confrontations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.61
    inence
    -0.57
    Viitteet
    -0.54
    кен
    -0.53
    mancy
    -0.52
     proper
    -0.51
    SharedCtor
    -0.51
     Historically
    -0.49
     base
    -0.49
    Izvori
    -0.49
    POSITIVE LOGITS
    bootstrapcdn
    0.76
    UrlEncoded
    0.59
     africains
    0.58
     fédé
    0.53
     officiers
    0.53
     shouted
    0.53
     énergé
    0.52
     yelling
    0.52
     frantically
    0.52
     déclar
    0.52
    Activations Density 0.343%

    No Known Activations