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. 19-GEMMASCOPE-RES-16K
    6. 417
    Prev
    Next
    INDEX
    Explanations

    indications of privacy concerns and the discussion surrounding sensitive information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropoda
    -0.57
    rag
    -0.49
     surla
    -0.48
    rage
    -0.47
    postcss
    -0.46
    '].'
    -0.46
     Weiss
    -0.44
    っか
    -0.44
    RuleContext
    -0.44
    <<"
    -0.44
    POSITIVE LOGITS
     personal
    1.82
     private
    1.70
    personal
    1.61
    Personal
    1.55
    private
    1.51
     Personal
    1.51
    PERSONAL
    1.43
     PERSONAL
    1.43
     privato
    1.39
     privata
    1.37
    Activations Density 0.185%

    No Known Activations