© 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. 17-GEMMASCOPE-RES-16K
    11. 12758
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the importance of minimizing negative impacts or maximizing positive outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.56
     Applied
    -0.47
    ibig
    -0.47
    <bos>
    -0.45
    uja
    -0.45
    ̩
    -0.45
    applied
    -0.45
     rw
    -0.44
     APPLIED
    -0.43
    int
    -0.43
    POSITIVE LOGITS
     möglichst
    1.38
    尽可能
    1.16
    できるだけ
    1.15
    なるべく
    1.07
     максимально
    1.00
     zoveel
    0.95
    尽量
    0.94
     ASAP
    0.93
     cât
    0.91
     sebanyak
    0.90
    Activations Density 0.377%

    No Known Activations