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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12022
    Prev
    Next
    INDEX
    Explanations

    code snippets that include import statements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.50
    Zunanje
    -0.50
    ığın
    -0.49
     íntima
    -0.49
     extérieures
    -0.47
     accett
    -0.47
     betaling
    -0.47
     assolutamente
    -0.46
     extérieurs
    -0.45
     esclavos
    -0.45
    POSITIVE LOGITS
    aarrggbb
    0.74
     os
    0.70
     requests
    0.69
     copy
    0.67
     snippetHide
    0.67
     CreateTagHelper
    0.67
    BagConstraints
    0.67
    CloseOperation
    0.65
     AssemblyCulture
    0.64
     logging
    0.63
    Activations Density 0.082%

    No Known Activations