© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6958
    Prev
    Next
    INDEX
    Explanations

    elements related to programming functions, particularly those that involve processing strings and headers in data

    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
    findpost
    -0.47
    ArgumentParser
    -0.47
    tagext
    -0.44
    Atsauces
    -0.38
    lihatkan
    -0.36
    сылкі
    -0.35
    Linki
    -0.35
    Kanpo
    -0.35
     externi
    -0.34
    nyataan
    -0.34
    POSITIVE LOGITS
     upper
    1.58
     lower
    1.44
     UPPER
    1.41
    upper
    1.40
     Upper
    1.40
    Upper
    1.40
    lower
    1.39
     lowercase
    1.38
     Lower
    1.34
     uppercase
    1.34
    Activations Density 0.374%

    No Known Activations