Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14828
    Prev
    Next
    INDEX
    Explanations

    references to technical issues or discussions related to remote access protocols

    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
    ſelf
    -0.50
     ſche
    -0.50
    ----</
    -0.47
    ammans
    -0.46
    WithIOException
    -0.46
    зулта
    -0.45
     resourceCulture
    -0.45
     Italijani
    -0.44
    ſelves
    -0.44
    transQ
    -0.42
    POSITIVE LOGITS
    GOTREF
    0.52
    ViewFeatures
    0.51
    今度は
    0.50
    Tikang
    0.47
    Again
    0.45
    AccessorTable
    0.44
    Sorry
    0.43
     étr
    0.41
     Stoff
    0.41
     Again
    0.40
    Activations Density 0.129%

    No Known Activations