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. 15380
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to iterative mathematical methods and convergence analysis

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

    "iteration" or repeating procedures

    np_acts-logits-general · gemini-2.0-flash

    iterative processes

    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
    rawDesc
    -0.39
    publicain
    -0.37
    richTextPanel
    -0.36
    Gambas
    -0.35
    iligt
    -0.35
     취
    -0.35
     Rumble
    -0.35
     avenir
    -0.35
    RequestMapping
    -0.34
    ári
    -0.33
    POSITIVE LOGITS
     iteration
    1.29
     iterations
    1.27
     iter
    1.24
     Iteration
    1.23
     iterative
    1.23
     Iter
    1.23
    迭代
    1.21
    Iteration
    1.18
     iterate
    1.16
    iteration
    1.05
    Activations Density 0.460%

    No Known Activations