© 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. 8995
    Prev
    Next
    INDEX
    Explanations

    specific combinations of letters and syllables that indicate certain names, titles, or technical terms

    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
    ្
    -0.43
    get
    -0.41
    ್
    -0.40
    ්
    -0.40
    ்
    -0.38
    🏻
    -0.38
    be
    -0.37
    -
    -0.37
     bes
    -0.36
    🏼
    -0.36
    POSITIVE LOGITS
     increí
    0.57
     indígen
    0.57
    ロウィン
    0.57
     esternos
    0.57
     $_(
    0.55
     queſta
    0.54
    featureID
    0.54
     iſt
    0.54
    iſen
    0.52
    הערות
    0.51
    Activations Density 0.748%

    No Known Activations