© 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. 9599
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that specify a defined or recognized entity

    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
    FunctionFlags
    -0.42
    bė
    -0.39
    地说道
    -0.39
    Cyfeiriadau
    -0.38
    (['
    -0.37
     purpoſe
    -0.37
     считается
    -0.37
    gsSP
    -0.36
     considérons
    -0.36
    [['
    -0.35
    POSITIVE LOGITS
    simply
    0.71
     simply
    0.68
     variously
    0.67
     informally
    0.59
    setVerticalGroup
    0.58
     collectively
    0.57
     referred
    0.56
     simplemente
    0.56
     semplicemente
    0.55
     kıs
    0.53
    Activations Density 0.292%

    No Known Activations