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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 975
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to patient treatment, specifically focusing on doses, reductions, and surgical interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    suggesting necessity or requirement

    np_acts-logits-general · gemini-2.0-flash

    need or require medical intervention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieteur
    -0.39
    béco
    -0.36
    ferous
    -0.36
    ństw
    -0.35
    errHandler
    -0.35
    Personendaten
    -0.33
    رشف
    -0.33
    
    -0.33
    TokenNameLBRACE
    -0.33
    DMETHOD
    -0.33
    POSITIVE LOGITS
     necessity
    0.86
     terpaksa
    0.83
     Necessity
    0.80
     Notwendigkeit
    0.79
    necess
    0.79
     necessitated
    0.78
    need
    0.74
     needed
    0.74
     пришлось
    0.73
     szükség
    0.73
    Activations Density 0.640%

    No Known Activations