© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3652
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names associated with various entities or characters

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

    Tokens after capitalized words

    np_acts-logits-general · gemini-2.0-flash

    Holiday Mansion, junar, KTLO, ao7b, Darroti

    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
     overall
    -0.44
    /*:
    -0.41
    დი
    -0.40
     actual
    -0.37
    principalTable
    -0.37
     ever
    -0.36
     Pain
    -0.36
    VARD
    -0.35
    anol
    -0.35
     Obrador
    -0.35
    POSITIVE LOGITS
    الدراسه
    0.61
    Viited
    0.59
    帖最后由
    0.56
     مرئيه
    0.54
     ivelany
    0.52
    colgante
    0.52
     nonUne
    0.52
     
    0.51
     يتيمه
    0.51
     ujednoznacz
    0.49
    Activations Density 0.577%

    No Known Activations