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. 21-GEMMASCOPE-RES-16K
    6. 807
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and well-wishing sentiments

    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
    LinkId
    -0.66
     AssemblyTitle
    -0.65
    XmlAccessType
    -0.63
    Зноскі
    -0.61
    Autoritní
    -0.48
     виправивши
    -0.47
    IntoConstraints
    -0.47
     GTO
    -0.47
    geslacht
    -0.46
    ⇓
    -0.46
    POSITIVE LOGITS
     hope
    3.21
     hopes
    2.71
    hope
    2.60
     Hope
    2.50
    Hope
    2.49
     hoping
    2.44
     hoped
    2.43
     HOPE
    2.33
    HOPE
    2.14
     hopeful
    2.06
    Activations Density 0.213%

    No Known Activations