© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5473
    Prev
    Next
    INDEX
    Explanations

    references to pads, particularly in the context of braking and absorbent materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibouti
    -0.74
    Архівовано
    -0.72
    __).
    -0.66
    minecraftforge
    -0.65
     Browne
    -0.63
     Turnbull
    -0.62
    MergeFrom
    -0.62
     uitges
    -0.62
    quehanna
    -0.62
    "]));
    -0.60
    POSITIVE LOGITS
     pad
    2.70
     pads
    2.60
     Pad
    2.58
     Pads
    2.48
    Pad
    2.48
    pad
    2.30
    Pads
    2.14
    pads
    2.12
     PAD
    2.12
    PAD
    2.04
    Activations Density 0.064%

    No Known Activations