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-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11628
    Prev
    Next
    INDEX
    Explanations

    phrases related to informed consent and patient privacy in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.48
     kasarigan
    -0.48
    GEBURTSDATUM
    -0.45
     surla
    -0.44
    IsMutable
    -0.40
    rrggbb
    -0.39
    المكان
    -0.39
     незавершена
    -0.39
     समीक्षाओं
    -0.38
    EndContext
    -0.38
    POSITIVE LOGITS
     consent
    2.06
     Consent
    1.71
    consent
    1.68
    Consent
    1.59
     permission
    1.55
     consents
    1.47
     consented
    1.39
     consentimiento
    1.34
     consentement
    1.29
     consenting
    1.26
    Activations Density 0.674%

    No Known Activations