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. 9-GEMMASCOPE-RES-16K
    6. 6836
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to data management and statistics

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

    before a comma, question mark, or period

    np_acts-logits-general · gemini-2.0-flash

    abstract nouns and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    picasso
    -0.68
    󠁴
    -0.62
    AISSEE
    -0.61
     Paglinawan
    -0.60
     MainAxisSize
    -0.60
    complexContent
    -0.60
     queſta
    -0.59
     surla
    -0.59
    ysuckle
    -0.58
    DockStyle
    -0.57
    POSITIVE LOGITS
     Keuangan
    0.40
     debería
    0.38
     initComponents
    0.37
     quaisquer
    0.37
     hubiera
    0.36
     deberían
    0.36
     Night
    0.35
     hubieran
    0.35
     vosotros
    0.35
     or
    0.35
    Activations Density 4.602%

    No Known Activations