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

    Neuronpedia

    APICircuit 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. 3-GEMMASCOPE-RES-16K
    6. 11025
    Prev
    Next
    INDEX
    Explanations

    the word "unless."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psons
    -0.69
    fought
    -0.65
    adeloupe
    -0.64
    /***/
    -0.63
    ɵɵelementEnd
    -0.60
    jutnya
    -0.59
    authier
    -0.59
     různ
    -0.58
    strips
    -0.57
     Beatty
    -0.57
    POSITIVE LOGITS
     unless
    2.49
    unless
    2.35
     Unless
    2.34
    Unless
    2.33
    除非
    1.51
     kecuali
    0.89
     necessariamente
    0.86
    LESS
    0.85
    InputBorder
    0.81
     without
    0.79
    Activations Density 0.039%

    No Known Activations