© 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
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7407
    Prev
    Next
    INDEX
    Explanations

    patterns related to technical specifications or structures in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.69
     '\\;'
    -0.69
    Personensuche
    -0.65
    SourceChecksum
    -0.61
    ftagPool
    -0.59
    UnknownFieldSet
    -0.58
    Controllo
    -0.57
    Дереккөздер
    -0.57
    Portail
    -0.56
    Hozzáférés
    -0.56
    POSITIVE LOGITS
    =
    0.39
    <_>
    0.28
    حياتها
    0.27
    EndContext
    0.26
    WriteLiteral
    0.26
    toxicity
    0.26
     tárgy
    0.25
    حياته
    0.24
    nezeu
    0.23
    iconque
    0.23
    Activations Density 0.156%

    No Known Activations