© 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. 7-GEMMASCOPE-RES-16K
    11. 13972
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases expressing conditions or causes and effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.22
     purpoſe
    -1.18
     poffible
    -1.07
     himſelf
    -1.07
     fubject
    -1.07
     Jefus
    -1.07
     ftate
    -1.04
     myſelf
    -1.02
     Efq
    -1.00
     houſe
    -1.00
    POSITIVE LOGITS
     and
    1.55
     And
    1.36
     AND
    1.34
     và
    1.32
    and
    1.20
     \&
    1.17
     и
    1.17
     και
    1.16
    Và
    1.13
    และ
    1.12
    Activations Density 1.345%

    No Known Activations