© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10622
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of paper and paper-related products

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

    "paper" and related terms

    np_acts-logits-general · gemini-2.0-flash

    paper and paper products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imprensa
    -0.47
     mesmas
    -0.45
     Versorgung
    -0.43
     raça
    -0.43
     trekken
    -0.42
     potência
    -0.41
     confiable
    -0.41
     Betriebs
    -0.41
     riesgos
    -0.41
     campanha
    -0.40
    POSITIVE LOGITS
     Paper
    1.22
     paper
    1.21
    Paper
    1.20
     PAPER
    1.13
    paper
    1.02
    PAPER
    1.02
     Papier
    1.00
     papers
    0.96
    Papers
    0.96
    Papier
    0.94
    Activations Density 0.136%

    No Known Activations