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. 1-GEMMASCOPE-RES-16K
    6. 6207
    Prev
    Next
    INDEX
    Explanations

    negation expressions or phrases indicating a lack of something

    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
     Arxivat
    -0.81
    脚注の使い方
    -0.80
    mybatisplus
    -0.62
    +#+#
    -0.61
    !?
    -0.56
     rentrée
    -0.55
     '`
    -0.54
    ///<
    -0.54
    oneofs
    -0.54
    AxisAlignment
    -0.54
    POSITIVE LOGITS
     !
    1.99
     !"
    1.33
     !)
    1.30
     !”
    1.29
     !.
    1.12
     !}
    1.12
     !'
    1.06
     !!!!!
    0.97
     !!!!
    0.95
     !!!
    0.92
    Activations Density 0.087%

    No Known Activations