© 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. 40-GEMMASCOPE-RES-16K
    11. 7401
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data or mathematical expressions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Twenty
    -0.75
     twenty
    -0.74
     Thirty
    -0.70
    Thirty
    -0.68
    twenty
    -0.68
    Twenty
    -0.63
     thirty
    -0.62
     twentieth
    -0.60
    thirty
    -0.57
     Forty
    -0.57
    POSITIVE LOGITS
    tagHelperRunner
    0.59
    SharedDtor
    0.45
     contextLoads
    0.38
     GenerationType
    0.37
     two
    0.36
    setDo
    0.36
     виправивши
    0.35
    MessageTagHelper
    0.34
     tow
    0.31
     zwei
    0.31
    Activations Density 0.681%

    No Known Activations