© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10791
    Prev
    Next
    INDEX
    Explanations

    references to various research activities or experiments related to scientific studies

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

    Comes before attribution (e.g. Analyzed the data:)

    np_acts-logits-general · gemini-2.0-flash

    and acts or omissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.55
    EndInit
    -0.48
    PhysRevD
    -0.48
     TestBed
    -0.47
     ostavi
    -0.46
    ImageContext
    -0.44
     east
    -0.44
    __*/
    -0.43
    ymce
    -0.43
     '\\
    -0.42
    POSITIVE LOGITS
    Personensuche
    0.62
     विश्वसनीयता
    0.61
     결과
    0.61
    httphttps
    0.58
     results
    0.58
    зульта
    0.57
     equipment
    0.56
    Результат
    0.55
    RESULTS
    0.53
     Majest
    0.53
    Activations Density 0.395%

    No Known Activations