© 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. 46750
    Prev
    Next
    INDEX
    Explanations

    references to academic publishers and their publications

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

    publisher names

    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-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
    Билгалдахарш
    -0.78
    transQ
    -0.76
     utafitiHapana
    -0.73
     disambiguazione
    -0.71
    aarrggbb
    -0.63
     يتيمه
    -0.61
    OrBuilder
    -0.61
    __':
    -0.60
     externi
    -0.59
    ьаж
    -0.59
    POSITIVE LOGITS
     Verlag
    0.51
     publishers
    0.44
     company
    0.43
     Publishing
    0.42
     publishing
    0.42
     Elsevier
    0.42
     Company
    0.41
     publisher
    0.41
     McGraw
    0.39
    Verlag
    0.39
    Activations Density 0.029%

    No Known Activations