© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 15443
    Prev
    Next
    INDEX
    Explanations

    terms related to enabling or disabling features and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    -0.56
    thâu
    -0.56
     ultimi
    -0.55
    gdx
    -0.54
    ."));
    -0.53
    sal
    -0.50
    rslt
    -0.50
    )~
    -0.50
     Fare
    -0.49
    POSITIVE LOGITS
    glEnable
    1.13
     OnEnable
    1.07
     disable
    0.96
    activate
    0.95
     Disable
    0.93
     disables
    0.93
     ENABLE
    0.93
     activate
    0.92
     deactivated
    0.91
     Disabled
    0.90
    Activations Density 0.171%

    No Known Activations