© 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. 38-GEMMASCOPE-RES-16K
    6. 14553
    Prev
    Next
    INDEX
    Explanations

    terms related to support and intervention in health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ism
    -1.34
    neath
    -0.96
    adays
    -0.91
    retudo
    -0.86
    theless
    -0.86
    side
    -0.78
    dehyde
    -0.77
    ISM
    -0.73
    nasium
    -0.71
    stuffs
    -0.69
    POSITIVE LOGITS
    IsContent
    0.45
    
    0.43
     referrerpolicy
    0.41
     golfe
    0.34
     DIAMOND
    0.33
    toggler
    0.33
     syns
    0.33
     PrintWriter
    0.32
    Remedy
    0.32
     asyncio
    0.31
    Activations Density 0.395%

    No Known Activations