© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8345
    Prev
    Next
    INDEX
    Explanations

    characters or sequences of letters and their representations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     B
    -0.73
     Ba
    -0.67
     BA
    -0.65
     BH
    -0.64
     Б
    -0.63
     ba
    -0.63
     BE
    -0.59
     Be
    -0.56
     Bu
    -0.56
     Bi
    -0.56
    POSITIVE LOGITS
    bed
    1.39
    bi
    1.18
    ben
    1.15
    by
    1.15
    b
    1.14
    bs
    1.10
    bit
    1.09
    bing
    1.09
    bas
    1.08
    bes
    1.06
    Activations Density 0.368%

    No Known Activations