© 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. 11870
    Prev
    Next
    INDEX
    Explanations

    URLs in a text

    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
     CURIAM
    -0.83
    parsedMessage
    -0.73
     ujednoznacz
    -0.71
     canst
    -0.67
    niſſe
    -0.65
     ſta
    -0.62
    astify
    -0.61
    esgue
    -0.60
    TextWatcher
    -0.60
     ſtre
    -0.60
    POSITIVE LOGITS
    ://
    1.92
    :\/\/
    0.87
    ://"
    0.82
    ="//
    0.74
     defaultstate
    0.59
    :///
    0.57
    import
    0.55
     the
    0.54
    ../../../
    0.53
     http
    0.53
    Activations Density 0.035%

    No Known Activations