Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 975
    Prev
    Next
    INDEX
    Explanations

    discussions about the benefits and applications of crochet in health and wellness contexts

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

    phrases expressing detailed explanations or elaborations of topics.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    MLLoader
    -0.68
     BIO
    -0.49
     SPORT
    -0.48
    Svg
    -0.48
     Pension
    -0.46
     antibio
    -0.46
     Tenta
    -0.46
     trig
    -0.46
     Currency
    -0.45
     CanadaChoose
    -0.45
    POSITIVE LOGITS
     miniaturka
    0.65
     AssemblyProduct
    0.54
     lenker
    0.48
     terecht
    0.47
    webElementXpaths
    0.43
    Geplaatst
    0.43
     środow
    0.43
    Panamoan
    0.43
     européennes
    0.43
    الإنجليزية
    0.42
    Activations Density 1.402%

    No Known Activations