© 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. 21-GEMMASCOPE-RES-16K
    11. 11978
    Prev
    Next
    INDEX
    Explanations

    references to items quantified as "large" or "huge" in scale or number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ActionListener
    -0.57
    awin
    -0.56
    ToCheck
    -0.54
    CppMethod
    -0.54
    ApiModelProperty
    -0.54
     TimeUnit
    -0.54
    RectangleBorder
    -0.53
    //{
    -0.52
    __":
    -0.52
     MenuView
    -0.52
    POSITIVE LOGITS
    Large
    1.09
     large
    1.08
     Large
    1.06
     LARGE
    1.05
    large
    1.03
    LARGE
    0.93
     larger
    0.82
     giant
    0.79
     big
    0.78
    giant
    0.77
    Activations Density 0.241%

    No Known Activations