© 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 EvalsExportsinterp-engineNEWAPI 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. 12905
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainty about circumstances or events

    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
    存在的
    -0.44
     wyst
    -0.40
    новниш
    -0.38
    れてる
    -0.35
    れている
    -0.35
    ここは
    -0.35
     występu
    -0.35
    actéristiques
    -0.34
     wynosi
    -0.34
    hibli
    -0.34
    POSITIVE LOGITS
     happen
    1.52
     happens
    1.51
     happened
    1.37
     HAPP
    1.25
    happen
    1.20
     Happen
    1.16
    happens
    1.15
     happ
    1.12
     happening
    1.11
    Happ
    1.05
    Activations Density 0.212%

    No Known Activations