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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13257
    Prev
    Next
    INDEX
    Explanations

    instances of 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 @ 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
     Lend
    -0.71
     Alb
    -0.68
     fight
    -0.67
     Rite
    -0.67
     }}">
    -0.66
     Frm
    -0.66
     Fight
    -0.66
    EN
    -0.65
    Rite
    -0.65
     Dalton
    -0.65
    POSITIVE LOGITS
    theless
    1.19
    +#+
    1.09
     However
    1.00
    however
    0.98
     Porém
    0.97
     however
    0.97
    unhofer
    0.94
     Cependant
    0.91
    zzleHttp
    0.88
    However
    0.87
    Activations Density 0.105%

    No Known Activations