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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12235
    Prev
    Next
    INDEX
    Explanations

    terms related to stakeholder engagement and research initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ComVisible
    -0.70
    ymce
    -0.60
    SourceChecksum
    -0.57
     gouvernements
    -0.57
    RuleContext
    -0.56
     racines
    -0.55
    tymologie
    -0.55
     esternos
    -0.55
    #+#
    -0.54
    elfde
    -0.53
    POSITIVE LOGITS
     new
    1.32
    new
    1.09
    新的
    1.08
     nueva
    1.07
    新
    1.03
     nuevos
    1.01
     nuevas
    1.00
     nieuwe
    0.98
     nuevo
    0.98
     NEW
    0.97
    Activations Density 0.233%

    No Known Activations