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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 5846
    Prev
    Next
    INDEX
    Explanations

    references to organizations and associations, particularly those related to policing and industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    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
    -0.48
     مفص
    -0.40
    Conclusie
    -0.33
    yntaxException
    -0.33
     Dirac
    -0.33
    Conclusão
    -0.32
     الحره
    -0.32
     ditemp
    -0.30
    ValueStyle
    -0.30
     Aguas
    -0.30
    POSITIVE LOGITS
     association
    1.97
     associations
    1.84
     Association
    1.84
    Association
    1.80
    association
    1.72
     Associations
    1.68
     ASSOCIATION
    1.66
    associations
    1.55
    Associations
    1.52
     asociación
    1.41
    Activations Density 0.335%

    No Known Activations