© 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 EvalsExportsinterp-engineNEWAPI 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. 8958
    Prev
    Next
    INDEX
    Explanations

    references to product specifications, particularly related to electronics or technology

    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
    <strong>
    -0.53
     puissant
    -0.52
     ,
    -0.51
     located
    -0.46
     אשר
    -0.44
     selected
    -0.43
      
    -0.42
     powerful
    -0.42
     approximately
    -0.42
     sogenannte
    -0.41
    POSITIVE LOGITS
     stuff
    1.13
     shitty
    1.03
     whatnot
    1.02
     crappy
    1.01
     autorytatywna
    1.01
    CloseOperation
    0.98
     thingy
    0.96
     fuckin
    0.95
     crap
    0.94
    whatever
    0.94
    Activations Density 1.884%

    No Known Activations