Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6247
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or hedging language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.69
    ſelf
    -0.67
     Reſ
    -0.66
     Majefty
    -0.66
    ſelves
    -0.66
     Winfrey
    -0.65
     Anſ
    -0.65
     Efq
    -0.64
     Houſe
    -0.62
     Monfieur
    -0.62
    POSITIVE LOGITS
     it
    0.80
    StructEnd
    0.76
     yeah
    0.74
     defaultstate
    0.74
    UnknownFieldSet
    0.73
     maybe
    0.72
     therefor
    0.71
     let
    0.71
     I
    0.70
     hopefully
    0.69
    Activations Density 0.141%

    No Known Activations