© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101448
    Prev
    Next
    INDEX
    Explanations

    references to high-definition (HD) technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brenn
    -0.44
    isNameExpr
    -0.44
     youre
    -0.42
    
    -0.42
     wynosi
    -0.41
     Pili
    -0.41
    नलिखित
    -0.40
    use
    -0.40
    you
    -0.40
    they
    -0.40
    POSITIVE LOGITS
     HD
    0.94
     hd
    0.91
    hd
    0.90
     Hd
    0.84
    HD
    0.82
    bd
    0.74
    Hd
    0.72
     bd
    0.71
     BD
    0.70
     BoxFit
    0.70
    Activations Density 0.012%

    No Known Activations