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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16072
    Prev
    Next
    INDEX
    Explanations

    exclamatory and emphatic punctuation marks that indicate strong feelings or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Exclamations and emphasis

    np_acts-logits-general · gemini-2.0-flash

    strong punctuation and exclamations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.65
     noDo
    -0.64
    存于互联网档案馆
    -0.64
    səhifə
    -0.64
     Мексичка
    -0.63
    ðsíða
    -0.62
    OGND
    -0.60
    Personendaten
    -0.59
    //}
    
    -0.57
     RequestMethod
    -0.57
    POSITIVE LOGITS
     Auff
    0.40
    1
    0.38
     Aufs
    0.38
    ing
    0.36
    ?.
    0.36
    !!
    0.36
     defStyle
    0.36
     Echt
    0.35
     Miß
    0.33
    ↵↵
    0.33
    Activations Density 0.143%

    No Known Activations