© 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. 21-GEMMASCOPE-RES-16K
    6. 12175
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight collaborative values and teamwork 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 @ 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
    reif
    -0.55
     doInBackground
    -0.55
     alphabetically
    -0.55
     actualité
    -0.54
    ็จ
    -0.53
     Процитовано
    -0.53
     Completing
    -0.52
    classnames
    -0.52
     rú
    -0.51
    ượt
    -0.50
    POSITIVE LOGITS
     promote
    1.44
     promotes
    1.42
     promoting
    1.34
     encourage
    1.33
     encourages
    1.29
     emphasis
    1.28
     emphasize
    1.27
     promoted
    1.25
     Promote
    1.24
    emphas
    1.24
    Activations Density 0.503%

    No Known Activations