© 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. 6577
    Prev
    Next
    INDEX
    Explanations

    specific statistical analysis terms and the presence of data evaluation methods

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

    Items in a series or list

    np_acts-logits-general · gemini-2.0-flash

    list selections

    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
    aarrggbb
    -0.52
    GTCX
    -0.49
     الحره
    -0.43
    SourceChecksum
    -0.39
     Савезне
    -0.39
    onDelete
    -0.38
    webElementXpaths
    -0.38
    Datuak
    -0.37
     resourceCulture
    -0.37
    Šaltiniai
    -0.37
    POSITIVE LOGITS
     candidates
    0.69
     lists
    0.60
     Candidates
    0.59
     selections
    0.54
     list
    0.53
     selection
    0.52
     winners
    0.52
    candidates
    0.52
     favorites
    0.51
     Selection
    0.49
    Activations Density 0.614%

    No Known Activations