© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 12198
    Prev
    Next
    INDEX
    Explanations

    industry-specific organizations and developments related to cancer treatment and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ➯
    -0.42
     getItemCount
    -0.41
     pouvoit
    -0.38
     feroit
    -0.36
    createCanvas
    -0.35
     étoit
    -0.35
    欲
    -0.35
     Catawiki
    -0.34
    SFC
    -0.34
    Rigidbody
    -0.34
    POSITIVE LOGITS
     patented
    0.72
     solutions
    0.65
     scalable
    0.64
     pioneered
    0.61
     products
    0.60
     technology
    0.59
     Lösungen
    0.59
     rozwiązania
    0.58
     proprietary
    0.58
     developed
    0.58
    Activations Density 0.362%

    No Known Activations