© 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. 36-GEMMASCOPE-RES-16K
    11. 13536
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases indicating decision-making or conditional scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彼の
    -0.79
    them
    -0.70
    him
    -0.68
    彼が
    -0.66
    彼女の
    -0.65
    Его
    -0.64
     ihn
    -0.63
    Их
    -0.63
    Him
    -0.60
     lui
    -0.59
    POSITIVE LOGITS
     he
    0.70
     camiset
    0.54
     mình
    0.49
    bildēt
    0.48
     she
    0.46
    šanai
    0.45
    를
    0.45
     miniaturka
    0.45
    ContentLoaded
    0.44
     we
    0.44
    Activations Density 2.189%

    No Known Activations