© 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. 10091
    Prev
    Next
    INDEX
    Explanations

    expressions related to necessity and action

    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
    ButtonGroup
    -0.54
    Tikang
    -0.49
    出版年
    -0.49
    migrationBuilder
    -0.49
     flèche
    -0.45
     Auge
    -0.45
    labelledby
    -0.45
    ();*/
    -0.45
     mola
    -0.44
    êche
    -0.44
    POSITIVE LOGITS
    只需要
    1.21
     merely
    1.13
    只需
    1.11
     wystarczy
    1.09
     simply
    1.06
     basta
    1.05
    只要
    1.04
     tinggal
    0.97
    simply
    0.96
    เพียง
    0.94
    Activations Density 0.306%

    No Known Activations