© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8500
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "conference" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.71
    солю
    -0.68
     utilis
    -0.67
     Vitro
    -0.65
    disposed
    -0.65
    roe
    -0.65
    셈
    -0.62
    orious
    -0.61
    kad
    -0.60
    tius
    -0.60
    POSITIVE LOGITS
     conferences
    2.28
     conference
    2.24
     Conference
    2.09
     Conferences
    2.07
    Conference
    2.02
     CONFERENCE
    1.90
    conference
    1.87
     Konferenz
    1.54
     conférence
    1.52
     conferencia
    1.44
    Activations Density 0.116%

    No Known Activations