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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11592
    Prev
    Next
    INDEX
    Explanations

    the presence of programming syntax and related constructs in code snippets

    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
     disambiguazione
    -0.96
    OGND
    -0.92
    tagHelperRunner
    -0.87
     initComponents
    -0.84
     AssemblyTitle
    -0.84
    GEBURTSDATUM
    -0.81
    Personensuche
    -0.80
    +#+#
    -0.80
     surla
    -0.80
     Efq
    -0.77
    POSITIVE LOGITS
    verne
    0.27
     törté
    0.27
     quần
    0.26
     سالم
    0.26
     tuyệt
    0.24
    <strong>
    0.24
     przy
    0.24
     érde
    0.24
    ReadKey
    0.24
    zucht
    0.24
    Activations Density 0.372%

    No Known Activations