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. 20-GEMMASCOPE-RES-16K
    6. 1168
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and operations

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

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    scientific or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RunWith
    -0.46
     religieuse
    -0.45
     pasteles
    -0.44
     religieuses
    -0.44
     complètes
    -0.43
    lüğ
    -0.43
     âgées
    -0.43
     sauvages
    -0.42
     quæ
    -0.42
     pleaſure
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.80
     surla
    0.68
    IntoConstraints
    0.68
     propOrder
    0.67
     kasarigan
    0.67
    ########.
    0.64
    richTextPanel
    0.63
     createSprite
    0.63
    RTLR
    0.59
    verifyException
    0.59
    Activations Density 1.584%

    No Known Activations