© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 1847
    Prev
    Next
    INDEX
    Explanations

    botanical terms and species related to flora

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

    scientific names of organisms, particularly species classifications.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.55
    bibinfo
    -0.52
    bibfield
    -0.51
    ombic
    -0.50
     وتسجيلات
    -0.50
    BibitemShut
    -0.50
     stiefel
    -0.49
     prest
    -0.49
    PreExecute
    -0.49
     myſelf
    -0.48
    POSITIVE LOGITS
     Савезне
    0.59
    UserScript
    0.57
     BorderRadius
    0.57
    <bos>
    0.54
    KISS
    0.54
    LabelTagHelper
    0.51
    RuleContext
    0.51
     funniest
    0.50
    waitKey
    0.50
    antwoorde
    0.49
    Activations Density 0.182%

    No Known Activations