© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 5500
    Prev
    Next
    INDEX
    Explanations

    specific programming-related definitions and structures such as data types and policies

    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
    transQ
    -0.60
    protoimpl
    -0.54
    OGND
    -0.53
    ########.
    -0.52
    tagHelperRunner
    -0.52
    writeFieldEnd
    -0.49
     ostavi
    -0.48
     ivelany
    -0.48
    qrstuvwxyz
    -0.47
    AndEndTag
    -0.44
    POSITIVE LOGITS
     different
    0.52
     tantôt
    0.48
    不同的
    0.47
     diferentes
    0.46
     Unterscheidung
    0.44
    diferentes
    0.43
     options
    0.42
     opciones
    0.41
    different
    0.40
     correspondant
    0.40
    Activations Density 0.725%

    No Known Activations