Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 77848
    Prev
    Next
    INDEX
    Explanations

    references to code, mathematical notation, and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical or code references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fine
    -0.39
     multi
    -0.38
     serious
    -0.37
     
    -0.35
     senior
    -0.34
     bi
    -0.33
     Persson
    -0.33
     “
    -0.32
     rev
    -0.32
     permanent
    -0.32
    POSITIVE LOGITS
    IsContent
    0.82
    PerformLayout
    0.67
    RenderAtEndOf
    0.66
    ſammen
    0.66
     Vikipedi
    0.63
    featureID
    0.61
     EconPapers
    0.60
     queſto
    0.60
    antası
    0.59
     ويكيپ
    0.58
    Activations Density 0.347%

    No Known Activations