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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6870
    Prev
    Next
    INDEX
    Explanations

    metaphors and comparisons in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     Infórmanos
    -0.67
     Numerade
    -0.62
     Autorisations
    -0.61
    MemoryWarning
    -0.57
    verwijspagina
    -0.57
    Спасылкі
    -0.56
     Autorizaciones
    -0.56
    KommentareTeilen
    -0.55
    expandindo
    -0.55
    +:+
    -0.54
    POSITIVE LOGITS
     analogy
    0.78
     analogies
    0.74
     resemblance
    0.72
     similarities
    0.66
     similarity
    0.66
     comparison
    0.65
     comparisons
    0.60
     resemb
    0.56
     likened
    0.56
    Comparisons
    0.54
    Activations Density 0.683%

    No Known Activations