© 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. 16-GEMMASCOPE-RES-16K
    11. 13011
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ****************
    -0.39
    odacty
    -0.37
     frigor
    -0.32
     MacGregor
    -0.32
     is
    -0.31
     Mon
    -0.31
     Muhammadu
    -0.31
     vå
    -0.30
     coroa
    -0.30
    _______________
    -0.30
    POSITIVE LOGITS
    help
    1.29
    helps
    1.25
    Help
    1.22
    helped
    1.22
    helping
    1.20
     Help
    1.20
     Helps
    1.19
     help
    1.18
    Helping
    1.14
    Helps
    1.14
    Activations Density 0.051%

    No Known Activations