© 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. 3-GEMMASCOPE-RES-16K
    11. 5067
    Prev
    Next
    INDEX
    Explanations

    the word "something."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    føl
    -0.47
    hånd
    -0.37
    kjø
    -0.36
    Bakgrunnsstoff
    -0.35
    Ārējās
    -0.35
     térmico
    -0.33
     regio
    -0.33
    OrEqual
    -0.33
    ือน
    -0.33
    miljø
    -0.33
    POSITIVE LOGITS
     something
    3.94
    something
    3.55
    Something
    3.48
     Something
    3.41
     SOMETHING
    2.89
     somethin
    2.52
     qualcosa
    2.41
     sesuatu
    2.23
     quelque
    2.13
     coś
    2.13
    Activations Density 0.036%

    No Known Activations