© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 16313
    Prev
    Next
    INDEX
    Explanations

    terms related to inner structures or components in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.96
    ]")]
    -0.85
    Portail
    -0.84
     suivantes
    -0.82
    RegressionTest
    -0.77
     rayures
    -0.76
     suivants
    -0.74
    CHOICES
    -0.74
     banknotes
    -0.74
     scythe
    -0.73
    POSITIVE LOGITS
     Inner
    1.51
     inner
    1.47
    Inner
    1.36
     Inside
    1.34
     INNER
    1.31
     interior
    1.30
     inside
    1.25
    Inside
    1.22
     Interior
    1.16
     INSIDE
    1.16
    Activations Density 0.140%

    No Known Activations