© 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. 10674
    Prev
    Next
    INDEX
    Explanations

    attributes and measurements related to scientific analysis and modeling

    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
     to
    -0.40
     thought
    -0.34
     Ram
    -0.32
    /
    -0.31
     Whit
    -0.31
     and
    -0.31
     a
    -0.31
    ½
    -0.31
     RAM
    -0.31
     Roos
    -0.31
    POSITIVE LOGITS
     ujednoznacz
    0.88
     &___
    0.87
     disambiguazione
    0.85
    JspWriter
    0.85
    IBOutlet
    0.81
    rrggbb
    0.77
     snippetHide
    0.77
    IntoConstraints
    0.76
    principalColumn
    0.75
    IUrlHelper
    0.75
    Activations Density 1.862%

    No Known Activations