© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 802
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to programming structures, specifically focusing on object-oriented programming and data management

    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
     AssemblyTitle
    -0.60
     enamorado
    -0.47
    føring
    -0.45
     alcanzado
    -0.43
    zunehmen
    -0.42
     kepem
    -0.42
    latego
    -0.42
     cesty
    -0.42
     étoit
    -0.41
    fører
    -0.40
    POSITIVE LOGITS
    ness
    0.85
    な
    0.66
    NESS
    0.65
    enough
    0.60
    LY
    0.60
    ly
    0.60
    ترین
    0.60
    하게
    0.59
     enough
    0.59
    
    0.57
    Activations Density 0.825%

    No Known Activations