© 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. 14455
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain character patterns within the text

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

    citation references in academic papers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    citation markers or reference numbers in academic text, particularly when they appear in brackets after commas.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    closing delimiter and punctuation sequences in scholarly/technical text, especially around citations, parentheses, brackets/braces, and LaTeX-style math or markup endings.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
     Мексичка
    -0.63
    <bos>
    -0.50
     թվական
    -0.50
     المعيارى
    -0.49
     CanadaChoose
    -0.48
     gynhyrchwyd
    -0.47
     ujednoznacz
    -0.46
    ècie
    -0.46
    すすめ
    -0.46
    RTLE
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.63
    তথ্যসূত্র
    0.56
    ագրություններ
    0.52
    -------
    0.40
    ...).
    0.40
    tibus
    0.38
    zelfde
    0.38
    、【
    0.37
    })->
    0.36
    ❤️❤️
    0.36
    Activations Density 2.066%

    No Known Activations