© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14503
    Prev
    Next
    INDEX
    Explanations

    details about game mechanics and their impact on player experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending in "-wise" or related to levels

    np_acts-logits-general · gemini-2.0-flash

    specify aspect with -wise or -level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chré
    -0.69
     kaarangay
    -0.54
    aulted
    -0.53
     avoient
    -0.51
    guarded
    -0.51
     Baillargeon
    -0.49
     fumée
    -0.49
     artesanales
    -0.49
     étoit
    -0.48
    tomation
    -0.47
    POSITIVE LOGITS
     wise
    0.74
    來說
    0.68
    wise
    0.66
    ecap
    0.65
    的には
    0.64
    而言
    0.63
    方面
    0.62
     terms
    0.61
    SequentialGroup
    0.61
    来说
    0.59
    Activations Density 0.381%

    No Known Activations