© 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. 21-GEMMASCOPE-RES-16K
    6. 13733
    Prev
    Next
    INDEX
    Explanations

    elements related to error handling and message display in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.53
    håll
    -0.52
     وتسجيلات
    -0.45
    lapsingToolbar
    -0.45
     StringTokenizer
    -0.43
     jsonify
    -0.42
    setopt
    -0.42
    խ
    -0.41
    enumii
    -0.41
     Pane
    -0.40
    POSITIVE LOGITS
    flashdata
    0.46
    TempData
    0.39
     Wicidata
    0.38
    enderror
    0.38
    IBarButtonItem
    0.36
    httphttps
    0.36
    fahrene
    0.36
     Vielen
    0.35
     referenties
    0.35
    SequentialGroup
    0.35
    Activations Density 0.158%

    No Known Activations