© 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. 18-GEMMASCOPE-RES-16K
    11. 13058
    Prev
    Next
    INDEX
    Explanations

    actions related to digging and excavation

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

    digging

    np_acts-logits-general · gemini-2.0-flash

    digging out

    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
    DotNetBar
    -0.68
    GEBURTSDATUM
    -0.68
    Portail
    -0.67
     <<<<<<<<<<<<<<
    -0.66
     disambiguazione
    -0.66
    Ծանոթ
    -0.65
     <=",
    -0.65
     שוליים
    -0.60
     Meksiku
    -0.57
     numberWith
    -0.57
    POSITIVE LOGITS
     digging
    1.49
     dug
    1.43
    Dig
    1.39
     Dig
    1.35
     dig
    1.31
     digger
    1.28
     digs
    1.25
    Dug
    1.07
     DIG
    1.06
    dug
    1.04
    Activations Density 0.079%

    No Known Activations