© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7533
    Prev
    Next
    INDEX
    Explanations

    instances of the word "paper" and its variations, indicating a focus on discussions about paper-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    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
     odol
    -0.37
     sztuki
    -0.35
     piemē
    -0.35
     opérateurs
    -0.35
     hierro
    -0.35
     versehen
    -0.34
     Dodson
    -0.34
     transmissão
    -0.34
     bestuur
    -0.34
    POSITIVE LOGITS
     Paper
    0.76
    Paper
    0.76
    Pap
    0.73
     Pap
    0.71
     PAPER
    0.68
    PAPER
    0.66
     PAP
    0.66
     المعيارى
    0.65
     pap
    0.63
     informée
    0.62
    Activations Density 0.150%

    No Known Activations