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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 3281
    Prev
    Next
    INDEX
    Explanations

    words indicating difficulty or hardship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ็จ
    -0.98
    Datuak
    -0.85
    __(/*!
    -0.81
    Zeneca
    -0.78
     McIn
    -0.77
    Obrázky
    -0.74
     برانيه
    -0.72
    DotNetBar
    -0.71
    Bats
    -0.70
     Firth
    -0.68
    POSITIVE LOGITS
     struggle
    1.53
     struggles
    1.46
     Struggle
    1.38
     struggling
    1.29
     struggled
    1.17
     strug
    1.06
    uggling
    1.05
    uggles
    1.02
    stru
    0.96
     Trou
    0.91
    Activations Density 0.062%

    No Known Activations