© 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. 9-GEMMASCOPE-RES-16K
    11. 5590
    Prev
    Next
    INDEX
    Explanations

    references to specific authors or notable scientific figures

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

    Surnames with "van", "der", "ter", or similar prefixes

    np_acts-logits-general · gemini-2.0-flash

    names like van der

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.57
     increí
    -0.56
    cakup
    -0.54
     مشين
    -0.50
    chufe
    -0.50
     Geschäft
    -0.48
     Erscheinung
    -0.48
    /**
    -0.47
     CreateTagHelper
    -0.47
    gonic
    -0.47
    POSITIVE LOGITS
     Van
    0.86
     VAN
    0.77
     van
    0.77
     von
    0.69
     Von
    0.68
     De
    0.66
    Van
    0.66
     de
    0.60
     ван
    0.60
     VON
    0.53
    Activations Density 0.431%

    No Known Activations