© 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. 21-GEMMASCOPE-RES-16K
    11. 1465
    Prev
    Next
    INDEX
    Explanations

    words related to scientific measurements and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieteur
    -0.62
    roek
    -0.61
    étisme
    -0.61
    Opens
    -0.58
    GraphicsUnit
    -0.58
    sivité
    -0.56
    reté
    -0.56
    imageshack
    -0.54
    ⓧ
    -0.54
    ApiOperation
    -0.54
    POSITIVE LOGITS
     treatment
    1.41
     treatments
    1.34
     treated
    1.27
     Treatment
    1.21
     Treatments
    1.21
    treatment
    1.17
    Treatment
    1.16
     TREATMENT
    1.12
    treated
    1.12
    Treatments
    1.07
    Activations Density 2.807%

    No Known Activations