© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14195
    Prev
    Next
    INDEX
    Explanations

    database-related terms and syntax used in SQL queries

    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
    aarrggbb
    -0.67
    yntaxException
    -0.62
    $_['
    -0.59
     ब्रेकडाउन
    -0.57
    IndentedString
    -0.56
    évaluateur
    -0.56
    multer
    -0.56
    SharedCtor
    -0.54
    __(/*!
    -0.52
    IntoConstraints
    -0.52
    POSITIVE LOGITS
    principalTable
    0.59
     tables
    0.39
    JoinTable
    0.38
    ībā
    0.33
     table
    0.33
    unicaciones
    0.33
    表
    0.33
     multip
    0.33
    Aux
    0.32
     sheets
    0.32
    Activations Density 0.296%

    No Known Activations