© 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. 21-GEMMASCOPE-RES-16K
    6. 16260
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to conflict and opposition in religious contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.61
    URLException
    -0.61
     estekak
    -0.60
     समीक्षाओं
    -0.59
    EndInit
    -0.59
     linkovi
    -0.57
     Wikimedijinoj
    -0.57
    Aholisi
    -0.57
    AutoScaleMode
    -0.56
    MessageOf
    -0.52
    POSITIVE LOGITS
     translators
    0.41
     translation
    0.35
    ologists
    0.34
     kế
    0.33
    CppMethod
    0.33
    tdb
    0.33
    larna
    0.32
     prostitutes
    0.32
     apunta
    0.32
    OrEqual
    0.32
    Activations Density 0.113%

    No Known Activations