© 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. 21-GEMMASCOPE-RES-16K
    6. 8965
    Prev
    Next
    INDEX
    Explanations

    specialized mathematical terms and structures within formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.54
    queryInterface
    -0.47
     ErrInvalid
    -0.43
     kiệm
    -0.42
    XtraEditors
    -0.41
     خارجية
    -0.41
    <?>
    -0.39
    GLOBALS
    -0.38
    kloped
    -0.38
    yan
    -0.38
    POSITIVE LOGITS
    =(
    1.29
     $(
    1.23
    }=(
    1.15
     }(
    1.13
     =(
    1.12
    ((
    1.09
    $(
    1.08
     $(\
    1.06
     tuple
    1.04
    tuple
    1.02
    Activations Density 0.592%

    No Known Activations