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. 15-GEMMASCOPE-RES-16K
    6. 2464
    Prev
    Next
    INDEX
    Explanations

    references to methods of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parentElement
    -0.71
     تق
    -0.71
    Hak
    -0.71
    sk
    -0.70
    ش
    -0.69
     Hak
    -0.69
     perse
    -0.69
    TR
    -0.67
    ck
    -0.67
     esper
    -0.67
    POSITIVE LOGITS
    httphttps
    1.26
     היתה
    0.96
     navideños
    0.91
    setMsg
    0.90
    etheless
    0.90
     ainfi
    0.89
    licet
    0.89
    ="<?=$
    0.87
    VIAF
    0.86
    æa
    0.86
    Activations Density 0.168%

    No Known Activations