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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15424
    Prev
    Next
    INDEX
    Explanations

    elements of personal experiences and emotional reactions related to reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.58
    mbito
    -0.49
    MathML
    -0.49
    stateProvider
    -0.49
    ParallelGroup
    -0.48
    cèse
    -0.44
    Personendaten
    -0.43
    manent
    -0.43
    pherals
    -0.40
    таратура
    -0.40
    POSITIVE LOGITS
     ویکی‌پدی
    0.53
     reader
    0.51
     pinulongan
    0.50
     viewers
    0.47
    IUrlHelper
    0.46
     дописавши
    0.45
     viewer
    0.45
     readers
    0.43
     immersive
    0.41
    ContentAsync
    0.41
    Activations Density 0.402%

    No Known Activations