© 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. 34-GEMMASCOPE-RES-16K
    11. 11701
    Prev
    Next
    INDEX
    Explanations

    references to physical structures and their functionalities

    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
    허
    -0.48
     Italijanski
    -0.41
    decre
    -0.41
    BibitemShut
    -0.41
     Decre
    -0.40
     informée
    -0.40
     endblock
    -0.38
     Decreased
    -0.38
    endforeach
    -0.38
    Decre
    -0.37
    POSITIVE LOGITS
     upward
    1.80
     rise
    1.63
     ascent
    1.59
     upwards
    1.55
     rising
    1.55
     lift
    1.51
     ascending
    1.48
     ascend
    1.45
     uplift
    1.43
     lifted
    1.41
    Activations Density 0.695%

    No Known Activations