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. 24-GEMMASCOPE-RES-16K
    6. 14059
    Prev
    Next
    INDEX
    Explanations

    programming keywords and constructs in the context of code snippets

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

    Strings, variables, and data structures in code

    np_acts-logits-general · gemini-2.0-flash

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     «
    -0.56
     ||
    
    -0.55
    «
    -0.54
     («
    -0.54
     "(
    -0.53
     reasonably
    -0.53
     (...)
    -0.53
     ``
    -0.52
     ({
    -0.52
     [{
    -0.51
    POSITIVE LOGITS
     temp
    0.83
     Temp
    0.65
     str
    0.64
    protoimpl
    0.63
    temp
    0.62
    myfile
    0.59
    oneofs
    0.58
     x
    0.58
     larmes
    0.57
    Temp
    0.56
    Activations Density 0.100%

    No Known Activations