© 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. 31-GEMMASCOPE-RES-16K
    11. 13414
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to non-English or foreign terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    apostrophes and contractions (particularly the possessive apostrophe in contractions like "1940's" and "day's").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.10
    BibitemShut
    -1.10
     témoig
    -1.04
    нгред
    -1.03
    niſſe
    -1.03
     ſind
    -1.03
    <unused80>
    -1.03
    <unused47>
    -1.02
    <unused16>
    -1.02
    <unused8>
    -1.02
    POSITIVE LOGITS
     bir
    0.31
     pol
    0.29
    ↵↵
    0.29
    </strong>
    0.29
    <eos>
    0.29
    ↵
    0.27
     ev
    0.27
    .
    0.27
     ile
    0.26
     ver
    0.26
    Activations Density 0.017%

    No Known Activations