© 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. 18-GEMMASCOPE-RES-16K
    11. 13339
    Prev
    Next
    INDEX
    Explanations

    key scientific terms related to biological processes and disorders

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

    Follows indefinite article ("a," "an")

    np_acts-logits-general · gemini-2.0-flash

    technical or multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.00
     Deshalb
    -0.99
     poffible
    -0.91
     fometimes
    -0.89
     Majefty
    -0.86
     ſeveral
    -0.85
     myſelf
    -0.84
     becauſe
    -0.81
     laſt
    -0.81
     perciò
    -0.80
    POSITIVE LOGITS
    に於
    0.80
     comuniques
    0.79
     delà
    0.75
     unknownFields
    0.70
    XmlAccessType
    0.70
     = 
    0.69
    Whilst
    0.68
    />
    0.68
     dibawah
    0.67
     Utilizing
    0.65
    Activations Density 0.983%

    No Known Activations