© 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. 22-GEMMASCOPE-RES-16K
    11. 12821
    Prev
    Next
    INDEX
    Explanations

    references to experimental techniques and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     probably
    -0.31
     probablemente
    -0.30
    Probably
    -0.28
     wahrscheinlich
    -0.27
     provavelmente
    -0.26
     Probably
    -0.26
     posiblemente
    -0.25
    probably
    -0.24
     possibly
    -0.24
     principalmente
    -0.24
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
     jadx
    0.80
     ProtoMessage
    0.73
    ContentAsync
    0.71
    OGND
    0.70
    parsedMessage
    0.70
     Numerade
    0.69
    AddTagHelper
    0.68
    المناصب
    0.67
     setShow
    0.67
    Activations Density 0.790%

    No Known Activations