Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3712
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts indicating additional information or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utched
    -0.69
     Woodford
    -0.68
    ="#"><
    -0.66
    monary
    -0.66
     setOpen
    -0.66
    ()==
    -0.66
     canteen
    -0.66
     végétale
    -0.66
    openqa
    -0.65
    ughty
    -0.64
    POSITIVE LOGITS
     addition
    2.22
    addition
    1.82
     Addition
    1.57
    Addition
    1.44
     additions
    1.36
     tillegg
    1.22
    Additionally
    1.17
     Additionally
    1.11
     entanto
    1.11
     Additions
    1.08
    Activations Density 0.147%

    No Known Activations