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. 25-GEMMASCOPE-RES-16K
    6. 1936
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their diagnoses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.80
    tagHelperRunner
    -0.76
    ViewFeatures
    -0.67
    
    -0.63
    richTextPanel
    -0.56
     jScrollPane
    -0.52
     useState
    -0.49
    ])):
    -0.49
     transférez
    -0.49
    例文帳に追加
    -0.48
    POSITIVE LOGITS
     condition
    0.97
     Condition
    0.81
     disorder
    0.81
    condition
    0.80
     diagnosis
    0.71
    Condition
    0.70
     CONDITION
    0.69
    nemia
    0.66
     condição
    0.61
    topic
    0.60
    Activations Density 0.839%

    No Known Activations