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. 15-GEMMASCOPE-RES-16K
    6. 5126
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate specificity or reference to particular items or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelper
    -0.56
    DBNull
    -0.53
    RunWith
    -0.52
    +#+#
    -0.51
     jScrollPane
    -0.48
    出版年
    -0.46
     Chwiliwch
    -0.46
    One
    -0.45
    richTextPanel
    -0.45
    boat
    -0.45
    POSITIVE LOGITS
     $_"
    0.67
    ")));
    
    0.66
    '}>
    0.63
    )"),
    0.61
     iconFacebook
    0.61
     RIPRODUZIONE
    0.61
    jenigen
    0.60
    )";
    
    0.60
     }}}{
    0.59
    NUMX
    0.59
    Activations Density 0.323%

    No Known Activations