© 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. 10909
    Prev
    Next
    INDEX
    Explanations

    references to social gatherings or events

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

    performing actions

    np_acts-logits-general · gemini-2.0-flash

    conduct and performing actions

    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
    UnknownFieldSet
    -0.65
     nakalista
    -0.61
     Biôgrafia
    -0.59
    UpdateCommand
    -0.54
    #
    -0.51
    InsertCommand
    -0.51
    Lähteet
    -0.50
    jspb
    -0.49
     Wikimédia
    -0.49
    ArgsConstructor
    -0.48
    POSITIVE LOGITS
     conducting
    1.01
     Conducting
    0.95
    Conduct
    0.92
     mengadakan
    0.92
     conducts
    0.90
     conduct
    0.85
     Conduct
    0.85
     undergo
    0.83
     menggelar
    0.81
     performing
    0.79
    Activations Density 0.453%

    No Known Activations