© 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. 11-GEMMASCOPE-RES-16K
    11. 4415
    Prev
    Next
    INDEX
    Explanations

    key phrases related to data analysis, project management, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⭗
    -0.59
     Efq
    -0.57
    𑄪
    -0.56
    𞤶
    -0.54
    𑄨
    -0.54
     Monfieur
    -0.54
    𑄬
    -0.54
    <unused20>
    -0.53
    <unused3>
    -0.53
    [@BOS@]
    -0.53
    POSITIVE LOGITS
     typelib
    0.50
     createState
    0.41
    Viitteet
    0.39
     różne
    0.36
    يكب
    0.35
    Ligações
    0.34
    Koordinaten
    0.34
     InputDecoration
    0.34
     various
    0.34
    labelledby
    0.33
    Activations Density 3.244%

    No Known Activations