© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 6818
    Prev
    Next
    INDEX
    Explanations

    references to the word "last" and its variations, indicating a focus on time or recency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beitragen
    -0.33
    ơi
    -0.29
     overwhelm
    -0.29
    hie
    -0.28
    dapat
    -0.28
     pies
    -0.27
     apre
    -0.27
    inkel
    -0.26
    EEEEEEEE
    -0.26
    вне
    -0.26
    POSITIVE LOGITS
     getLast
    0.74
    resort
    0.70
     resort
    0.69
    Resort
    0.68
     utafitiHapana
    0.67
    ingly
    0.66
     Dernière
    0.65
     CreateTagHelper
    0.65
     Last
    0.65
     ModelExpression
    0.64
    Activations Density 0.084%

    No Known Activations