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. 23-GEMMASCOPE-RES-16K
    6. 11797
    Prev
    Next
    INDEX
    Explanations

    text related to medical diagnosis and testing accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istoitu
    -0.56
     StatelessWidget
    -0.54
    archiviato
    -0.52
     Wikimedijinoj
    -0.51
     StatefulWidget
    -0.48
     GenerationType
    -0.48
     constexpr
    -0.47
    SPATH
    -0.47
    GraphicsUnit
    -0.46
    ductory
    -0.46
    POSITIVE LOGITS
     detection
    2.23
     detecting
    2.09
     detect
    2.08
     identification
    2.07
     detected
    2.07
     identifying
    2.00
     Detection
    1.98
     identify
    1.94
     detects
    1.91
     Detect
    1.90
    Activations Density 1.227%

    No Known Activations