© 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. 38-GEMMASCOPE-RES-16K
    11. 7501
    Prev
    Next
    INDEX
    Explanations

    expressions indicating issues of crime and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.69
     مفص
    -0.46
    yntaxException
    -0.46
     الحره
    -0.44
    WireFormatLite
    -0.44
     فريبيس
    -0.43
     كومونز
    -0.38
    ⚭
    -0.38
    othes
    -0.37
     OFDb
    -0.37
    POSITIVE LOGITS
     association
    1.31
     associations
    1.27
     Association
    1.21
    Association
    1.20
    association
    1.14
     Associations
    1.13
     ASSOCIATION
    1.11
    associations
    1.09
     Federation
    1.04
     federation
    1.02
    Activations Density 0.307%

    No Known Activations