© 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. 2-GEMMASCOPE-RES-16K
    6. 13903
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "capture" and its variations, indicating a focus on the concept of capturing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TemporalType
    -0.46
    Lleg
    -0.40
    UFACT
    -0.35
     emperador
    -0.34
    iornamento
    -0.33
    ⓧ
    -0.33
     échelle
    -0.33
     évaluation
    -0.31
     onAnimation
    -0.31
    นี่
    -0.30
    POSITIVE LOGITS
     captured
    1.02
     capture
    1.01
     capturing
    0.96
    capture
    0.88
     Capture
    0.87
    Capture
    0.85
     captures
    0.84
    captured
    0.82
    Captured
    0.78
     captive
    0.77
    Activations Density 0.033%

    No Known Activations