© 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. 3-GEMMASCOPE-RES-16K
    6. 13575
    Prev
    Next
    INDEX
    Explanations

    references to specific genes or genetic sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ་་
    -1.31
     itſelf
    -1.21
     Anſ
    -1.14
     ―――――
    -1.10
     themſelves
    -1.06
     myſelf
    -1.06
     ſeveral
    -1.05
     Theſe
    -1.04
     faſt
    -1.01
     ſever
    -1.01
    POSITIVE LOGITS
     R
    1.42
     P
    1.39
     S
    1.39
     M
    1.39
     K
    1.39
     D
    1.36
     O
    1.35
     W
    1.33
     L
    1.33
     C
    1.33
    Activations Density 0.648%

    No Known Activations