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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7232
    Prev
    Next
    INDEX
    Explanations

    German phrases and technical terms related to the use and behavior of modifiers in various contexts, particularly in programming and linguistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inSlope
    -0.52
     transférez
    -0.52
     bParam
    -0.48
    MessageTagHelper
    -0.48
     springfox
    -0.48
    bootstrapcdn
    -0.47
    wnia
    -0.47
    #+#
    -0.46
    ंदीखरीदारी
    -0.43
    RegressionTest
    -0.43
    POSITIVE LOGITS
    astéroïdes
    0.41
     '\\;'
    0.39
     عز
    0.39
    APPLAUSE
    0.38
     Melrose
    0.38
     SF
    0.36
     Lur
    0.36
     compli
    0.36
    setView
    0.36
     initComponents
    0.36
    Activations Density 0.572%

    No Known Activations