© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6733
    Prev
    Next
    INDEX
    Explanations

    the presence of the prefix "con-" in words and terms

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

    terms related to "con" or "consecutive," indicating connections or sequences in various contexts

    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
     Theſe
    -1.19
    BibitemShut
    -1.09
     ainfi
    -1.05
    ^(@)
    -1.03
     Efq
    -1.03
     varandra
    -1.02
    FieldBuilder
    -1.00
    ModelSerializer
    -0.98
    mereka
    -0.97
    Reprodução
    -0.95
    POSITIVE LOGITS
    Con
    2.38
     Con
    2.26
    con
    2.20
    CON
    1.98
     CON
    1.97
     con
    1.87
     kon
    1.32
     cons
    1.31
     Kon
    1.29
    Cons
    1.26
    Activations Density 0.137%

    No Known Activations