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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 7629
    Prev
    Next
    INDEX
    Explanations

    the presence of whitespace or empty space characters in text

    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
    QMetaType
    -0.93
    ImageContext
    -0.86
     tartalomajánló
    -0.85
     estekak
    -0.80
    RectangleBorder
    -0.76
     ModelExpression
    -0.76
    kloped
    -0.75
     '\\;'
    -0.75
     الرياضيه
    -0.72
    MessageTagHelper
    -0.71
    POSITIVE LOGITS
    <h3>
    0.58
    <h6>
    0.53
    <b>
    0.52
    <h4>
    0.51
     
    0.51
    <h2>
    0.50
    <h5>
    0.45
     Holocene
    0.44
    ინ
    0.43
    </i>
    0.42
    Activations Density 0.298%

    No Known Activations