© 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. 23-GEMMASCOPE-RES-16K
    6. 9717
    Prev
    Next
    INDEX
    Explanations

    references to locations or contexts within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    紹介します
    -0.66
    考える
    -0.64
     verrez
    -0.62
    美国
    -0.61
     linkovi
    -0.56
    urlopen
    -0.56
    中国
    -0.56
    Viitteet
    -0.55
    狙
    -0.55
    rungsseite
    -0.54
    POSITIVE LOGITS
     terms
    1.32
     accordance
    1.32
     lieu
    1.24
     spite
    1.24
     relation
    1.22
     addition
    1.18
     conjunction
    1.16
     regards
    1.14
     the
    1.10
     order
    1.09
    Activations Density 1.181%

    No Known Activations