© 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. 2-GEMMASCOPE-RES-16K
    11. 4812
    Prev
    Next
    INDEX
    Explanations

    references to conversations or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MBR
    -0.38
     Crea
    -0.38
    уна
    -0.36
    VersionUID
    -0.36
    気に入
    -0.35
    gento
    -0.35
     EconPapers
    -0.34
    leece
    -0.34
     Mn
    -0.34
     MiG
    -0.34
    POSITIVE LOGITS
     talk
    3.61
    talk
    3.17
     Talk
    3.09
     TALK
    3.03
    Talk
    2.98
     talked
    2.97
     talking
    2.83
     talks
    2.75
    TALK
    2.63
    talking
    2.53
    Activations Density 0.184%

    No Known Activations