© 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. 12807
    Prev
    Next
    INDEX
    Explanations

    information related to upcoming events and scheduling details

    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
    DeleteBehavior
    -0.54
    setCharacter
    -0.49
    MigrationBuilder
    -0.48
    webElementXpaths
    -0.47
    aarrggbb
    -0.46
     triom
    -0.45
     estrena
    -0.45
    CodeAttribute
    -0.43
    ChildScrollView
    -0.43
    见证
    -0.42
    POSITIVE LOGITS
     flirt
    0.74
     discussions
    0.73
     Gespräche
    0.70
     flir
    0.69
     interested
    0.68
     interest
    0.67
     tentative
    0.66
     рассматри
    0.65
     talks
    0.63
     tentatively
    0.62
    Activations Density 0.462%

    No Known Activations