© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11164
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to places or locations

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

    Place names followed by parenthetical abbreviations

    np_acts-logits-general · gemini-2.0-flash

    city names in datelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Италијани
    -0.74
    oa̍t
    -0.74
    transQ
    -0.66
     للمعارف
    -0.66
     Савезне
    -0.65
     ब्रेकडाउन
    -0.65
     noDo
    -0.64
    EndGlobalSection
    -0.64
    tanleria
    -0.63
    majánló
    -0.62
    POSITIVE LOGITS
    ISupport
    0.38
    IContainer
    0.37
     conclusion
    0.36
    complexContent
    0.35
     doInBackground
    0.35
     J
    0.34
     mergeFrom
    0.34
    -
    0.31
    J
    0.31
     neighborhood
    0.29
    Activations Density 0.062%

    No Known Activations