© 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. 15-GEMMASCOPE-RES-16K
    11. 7247
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts associated with mechanical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.80
    bpp
    -0.60
    frastructure
    -0.59
    ResumeLayout
    -0.59
    ⓧ
    -0.58
    BeginContext
    -0.58
    LOAT
    -0.57
    ."</
    -0.57
     '\\;'
    -0.57
    Билгалдахарш
    -0.57
    POSITIVE LOGITS
     режим
    0.49
     rêver
    0.48
     mód
    0.48
     témoins
    0.48
     alimentação
    0.48
     philosophie
    0.47
     laterales
    0.47
     preset
    0.47
    PropTypes
    0.46
     voisins
    0.46
    Activations Density 1.270%

    No Known Activations