© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4810
    Prev
    Next
    INDEX
    Explanations

    medical terms related to pathology and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IAN
    -0.51
    IA
    -0.50
    IANO
    -0.47
    ÍAS
    -0.46
    ConstraintMaker
    -0.45
    IANE
    -0.45
    yaf
    -0.43
    IAS
    -0.43
    IANS
    -0.42
    ian
    -0.42
    POSITIVE LOGITS
    izio
    0.49
     Burning
    0.45
    icio
    0.44
    __':
    
    0.44
    icius
    0.39
    cinia
    0.38
    Burning
    0.38
    mario
    0.38
     scio
    0.38
     cio
    0.38
    Activations Density 0.442%

    No Known Activations