© 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. 33-GEMMASCOPE-RES-16K
    11. 5434
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurement and validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.46
    BeginContext
    -0.35
    theless
    -0.35
     Réponses
    -0.35
    enseits
    -0.34
    évaluateur
    -0.34
    []
    -0.34
    しかも
    -0.33
    meanor
    -0.32
     *>(
    -0.32
    POSITIVE LOGITS
     refers
    2.03
     refer
    1.39
     referring
    1.31
     désigne
    1.30
    指的是
    1.25
    是指
    1.22
    refer
    1.19
     refiere
    1.13
     bezeichnet
    1.11
     describes
    1.09
    Activations Density 1.105%

    No Known Activations