© 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. 4-GEMMASCOPE-RES-16K
    6. 13344
    Prev
    Next
    INDEX
    Explanations

    words of conclusion or transitional phrases indicating a result or consequence

    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
     LON
    -0.71
     Sarg
    -0.69
    lipop
    -0.68
    ateral
    -0.66
    pee
    -0.65
     Whal
    -0.65
     Apre
    -0.64
     Alton
    -0.64
    eara
    -0.63
     Bernadette
    -0.63
    POSITIVE LOGITS
     thus
    2.23
    thus
    1.96
     Thus
    1.92
    Thus
    1.87
     hence
    1.46
    Ainsi
    1.46
     therefore
    1.44
     Ainsi
    1.38
     Hence
    1.35
    Hence
    1.34
    Activations Density 0.141%

    No Known Activations