© 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. 20-GEMMASCOPE-RES-16K
    6. 14687
    Prev
    Next
    INDEX
    Explanations

    programming syntax and operations related to searching and filtering based on string content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.51
    UIControlState
    -0.48
    richTextPanel
    -0.47
    BagConstraints
    -0.47
    請繼續往下閱讀
    -0.46
    HasAnnotation
    -0.46
     Chwiliwch
    -0.45
     createStore
    -0.44
    enterOuterAlt
    -0.44
     seg
    -0.44
    POSITIVE LOGITS
     irgende
    0.50
    startswith
    0.48
    PREFIX
    0.45
    verifyException
    0.45
     liknande
    0.43
     billeder
    0.43
    arraycopy
    0.42
     έν
    0.42
    startsWith
    0.42
     irgend
    0.42
    Activations Density 0.191%

    No Known Activations