© 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. 12-GEMMASCOPE-RES-16K
    6. 9832
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and method calls in Android programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tegas
    -0.38
     amarilla
    -0.36
     utafitiHapana
    -0.35
     cellspacing
    -0.35
     oeil
    -0.35
    цезда
    -0.33
     Irán
    -0.33
     helicóptero
    -0.33
     peixe
    -0.33
     tæ
    -0.33
    POSITIVE LOGITS
    Bundle
    2.80
     Bundle
    2.27
     bundle
    2.03
    bundle
    1.91
     bundles
    1.74
    Bundles
    1.66
    bundles
    1.57
     Bund
    1.53
    UNDLE
    1.42
    Bund
    1.33
    Activations Density 0.071%

    No Known Activations