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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 11503
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وصلات
    -0.31
    MUT
    -0.31
    <bos>
    -0.31
    vertra
    -0.30
     genuinely
    -0.30
    UnitTesting
    -0.28
     etc
    -0.28
     Nip
    -0.28
    zus
    -0.28
    tanleria
    -0.28
    POSITIVE LOGITS
    ]")]
    0.79
    hdashline
    0.72
    onOptions
    0.70
    AutoresizingMask
    0.62
     تضيفلها
    0.62
    ">//
    0.61
     Paglinawan
    0.61
    errHandler
    0.61
    IBOutlet
    0.60
    Autoritní
    0.60
    Activations Density 0.218%

    No Known Activations