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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9109
    Prev
    Next
    INDEX
    Explanations

    the word "however."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resultCode
    -0.65
    ']==
    -0.62
    ftagPool
    -0.61
    ":["
    -0.59
    ]}{
    -0.58
    ubri
    -0.57
    imet
    -0.57
    fml
    -0.56
    ()==
    -0.55
    ():
    -0.55
    POSITIVE LOGITS
     however
    4.29
    however
    3.81
     entanto
    2.83
    However
    2.75
     However
    2.68
     cependant
    2.44
     tuttavia
    2.33
     però
    2.29
     porém
    2.23
     însă
    2.08
    Activations Density 0.114%

    No Known Activations