© 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. 22-GEMMASCOPE-RES-16K
    11. 8377
    Prev
    Next
    INDEX
    Explanations

    measurement units and dimensions in scientific contexts

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

    Exponents, especially negative exponents

    np_acts-logits-general · gemini-2.0-flash

    inverse units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.79
     complied
    -0.53
     distor
    -0.52
     مفص
    -0.52
     distortions
    -0.51
     Andro
    -0.50
    Geplaatst
    -0.50
     Worcester
    -0.50
    preuve
    -0.50
     Dist
    -0.50
    POSITIVE LOGITS
    ^{-
    1.55
    }^{-
    1.49
    )^{-
    1.30
     inverse
    1.29
    ]^{-
    1.24
     }^{-
    1.19
     ^{-
    1.14
    $^{-
    1.09
    inverse
    1.09
     Inverse
    1.02
    Activations Density 0.704%

    No Known Activations