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. 19-GEMMASCOPE-RES-16K
    6. 320
    Prev
    Next
    INDEX
    Explanations

    references to musical works and their associated artists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ništvo
    -0.61
    RegressionTest
    -0.61
    ibol
    -0.57
    baric
    -0.56
    umatic
    -0.56
    forChild
    -0.55
     Sections
    -0.55
    orsese
    -0.55
     Stored
    -0.54
    Ndr
    -0.54
    POSITIVE LOGITS
     debut
    0.74
     released
    0.71
     releasing
    0.71
     release
    0.71
     releases
    0.69
     EP
    0.67
    release
    0.64
    self
    0.64
     self
    0.63
     pubblicazione
    0.62
    Activations Density 0.127%

    No Known Activations