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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5518
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "dig" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.87
    protoimpl
    -0.83
    الحياه
    -0.73
     <<<<<<<<<<<<<<
    -0.72
    Rhestr
    -0.70
    extAlignment
    -0.68
    InjectAttribute
    -0.66
    enterOuterAlt
    -0.65
    WebVitals
    -0.65
    tvguidetime
    -0.64
    POSITIVE LOGITS
     dig
    3.63
    Dig
    3.32
     Dig
    3.31
     digging
    2.77
    dig
    2.77
     dug
    2.60
     digs
    2.59
     DIG
    2.54
    DIG
    2.31
     digger
    1.94
    Activations Density 0.051%

    No Known Activations