© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9811
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of "early" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vstack
    -0.45
    vestream
    -0.44
    setVerticalGroup
    -0.42
    TypedDataSet
    -0.40
     suing
    -0.40
    .$.
    -0.40
    grine
    -0.40
    iov
    -0.40
    vensis
    -0.39
    usti
    -0.38
    POSITIVE LOGITS
    Early
    0.96
     Early
    0.94
     early
    0.89
     EARLY
    0.88
    early
    0.84
    EARLY
    0.84
    早
    0.78
     temprano
    0.71
     morning
    0.68
     temprana
    0.65
    Activations Density 0.151%

    No Known Activations