© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 10606
    Prev
    Next
    INDEX
    Explanations

    terms related to frequency of occurrence, particularly those indicating daily or regular activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coste
    -0.65
    __(/*!
    -0.64
     THING
    -0.62
    มาะ
    -0.61
     PyObject
    -0.60
    Thing
    -0.58
    i
    -0.58
    нке
    -0.58
    e
    -0.58
     Thing
    -0.58
    POSITIVE LOGITS
     daily
    1.41
    daily
    1.38
     DAILY
    1.36
     Daily
    1.35
    DAILY
    1.35
    Daily
    1.29
    paravant
    1.17
     hourly
    1.12
     Weekly
    1.10
     WEEKLY
    1.09
    Activations Density 0.089%

    No Known Activations