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. 16-GEMMASCOPE-RES-16K
    6. 66
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistical information related to survey responses and demographics

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

    Numerical data and statistics

    np_acts-logits-general · gemini-2.0-flash

    quantities and proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.69
    DebuggerNonUser
    -0.66
     Pingback
    -0.66
    HttpPut
    -0.63
    irited
    -0.62
     pstmt
    -0.61
    typeparam
    -0.61
    IsPostBack
    -0.61
    ///
    
    -0.59
     
    -0.59
    POSITIVE LOGITS
     approximately
    0.80
    approximately
    0.70
     roughly
    0.68
     (~
    0.67
     Approximately
    0.65
     ($
    0.65
     six
    0.64
     approx
    0.64
     =
    0.63
     amounting
    0.61
    Activations Density 0.519%

    No Known Activations