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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 14748
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas related to statistical modeling

    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
    ScopeManager
    -0.42
     مرئيه
    -0.40
     Komponist
    -0.36
    RotationOrder
    -0.33
    Diweddarwch
    -0.33
     souligné
    -0.32
    Engineers
    -0.31
    Archite
    -0.31
    /*
    -0.30
    JLabel
    -0.30
    POSITIVE LOGITS
    +#+#
    0.73
     يتيمه
    0.61
    InputTagHelper
    0.58
    nsito
    0.50
    AutoModerator
    0.50
    deleteById
    0.49
    yntaxException
    0.49
    errHandler
    0.48
    XmlSchema
    0.48
     Rtl
    0.47
    Activations Density 1.258%

    No Known Activations