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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 261
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation, particularly involving brackets and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     C
    -0.59
    es
    -0.57
     nu
    -0.57
    -
    -0.55
    ure
    -0.54
     ven
    -0.53
     ses
    -0.53
     A
    -0.53
    newArrayList
    -0.53
     Mar
    -0.52
    POSITIVE LOGITS
    \[
    1.24
    \]
    1.06
    awtextra
    1.00
     \[
    0.96
     ―――――
    0.95
     дописавши
    0.95
     \]
    0.91
     uſ
    0.90
     Перейти
    0.88
     présidentielle
    0.88
    Activations Density 0.161%

    No Known Activations