© 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. 35-GEMMASCOPE-RES-16K
    11. 8472
    Prev
    Next
    INDEX
    Explanations

    keys and methods related to programming implementation practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лтемелер
    -0.44
    edip
    -0.39
     ComVisible
    -0.39
     препратки
    -0.37
    fürst
    -0.35
    Enumerable
    -0.33
    Queryable
    -0.32
    estimable
    -0.32
    sendRedirect
    -0.32
     whither
    -0.32
    POSITIVE LOGITS
     approach
    2.48
     method
    2.19
     methodology
    2.11
    approach
    2.09
     technique
    2.05
     Approach
    1.88
     approaches
    1.82
    Approach
    1.81
     strategy
    1.81
     methods
    1.81
    Activations Density 2.591%

    No Known Activations