© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13999
    Prev
    Next
    INDEX
    Explanations

    key metrics and statistical data related to performance or outcomes in research and legal contexts

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

    Tokens before certain words (rate, for, by, in)

    np_acts-logits-general · gemini-2.0-flash

    request for

    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
     ujednoznacz
    -0.48
    ⓧ
    -0.31
     brukar
    -0.27
     <=",
    -0.27
    nmgp
    -0.27
    igrafi
    -0.27
     yyr
    -0.27
     Näch
    -0.26
     faldas
    -0.26
    压
    -0.26
    POSITIVE LOGITS
    Билгалдахарш
    0.65
    consulté
    0.62
    bewerken
    0.62
     الاطلاع
    0.58
    enumii
    0.57
    #+#
    0.56
    elebr
    0.53
     فريبيس
    0.53
    munk
    0.52
    Климат
    0.51
    Activations Density 2.090%

    No Known Activations