Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2016
    Prev
    Next
    INDEX
    Explanations

    phrases related to peer support and group interactions in therapeutic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zyden
    -0.42
     Wayback
    -0.40
    cipes
    -0.38
    Exceeded
    -0.37
    QMetaType
    -0.37
    ätzlich
    -0.36
     Interim
    -0.35
    meris
    -0.35
    zydent
    -0.35
     Barbier
    -0.34
    POSITIVE LOGITS
     group
    2.31
     groups
    2.28
    group
    2.05
    groups
    1.96
     Groups
    1.94
     groupe
    1.93
     GROUP
    1.90
     grouping
    1.84
     GROUPS
    1.84
     grupo
    1.84
    Activations Density 0.903%

    No Known Activations