© 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. 6161
    Prev
    Next
    INDEX
    Explanations

    technical terms related to documentation and operations

    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
     règle
    -0.44
    marle
    -0.44
    тивность
    -0.44
    क्ट
    -0.44
    ตร์
    -0.43
    anterie
    -0.42
    衛門
    -0.42
    Nib
    -0.42
    LikeLike
    -0.42
     Frisch
    -0.41
    POSITIVE LOGITS
    ation
    1.29
    tion
    1.26
    tions
    1.18
    ations
    1.17
    ATION
    1.14
     tion
    1.12
     ation
    1.03
    ational
    1.02
     tions
    0.98
    TION
    0.96
    Activations Density 0.350%

    No Known Activations