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. 15578
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to graphical user interface layouts in programming

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

    Code snippets containing numbers and symbols

    np_acts-logits-general · gemini-2.0-flash

    size assignment

    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
     AssemblyCompany
    -0.47
    Története
    -0.46
    DockStyle
    -0.45
     المعيارى
    -0.43
     Biôgrafia
    -0.42
     otomatig
    -0.42
      
    -0.39
    ########.
    -0.39
    <eos>
    -0.37
    principalColumn
    -0.36
    POSITIVE LOGITS
    httphttps
    0.58
     mouseClicked
    0.52
    ᐝ
    0.49
    awtextra
    0.49
     CreateTagHelper
    0.47
     ſein
    0.47
     parallelogram
    0.47
     tymp
    0.46
    ḳ
    0.45
     Audiodateien
    0.44
    Activations Density 0.017%

    No Known Activations