© 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. 5-GEMMASCOPE-RES-16K
    11. 2926
    Prev
    Next
    INDEX
    Explanations

    phrases indicating directionality, specifically movements up or down 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.52
    illa
    -0.51
    tetten
    -0.51
    mektedir
    -0.50
    Lar
    -0.47
     sebe
    -0.46
    tské
    -0.46
     kli
    -0.46
    emiah
    -0.46
    が出
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.78
    mybatisplus
    0.76
    +#+
    0.72
     vägen
    0.70
    
    0.67
     gennem
    0.65
    PreferredItem
    0.63
     Administrativna
    0.63
     вдоль
    0.62
    skjaer
    0.61
    Activations Density 0.121%

    No Known Activations