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. 18-GEMMASCOPE-RES-16K
    6. 681
    Prev
    Next
    INDEX
    Explanations

    specific numerical data, particularly ages and other statistics related to people

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

    Age in years

    np_acts-logits-general · gemini-2.0-flash

    ages expressed with year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.54
    RSpec
    -0.51
    ()?;
    -0.50
    ']).
    -0.49
     
    -0.48
    pett
    -0.46
    endency
    -0.45
    oples
    -0.44
     Infórmanos
    -0.44
    ')}}">
    -0.44
    POSITIVE LOGITS
    GeneratedValue
    0.67
    Revenir
    0.64
    tagHelperRunner
    0.60
    ⓧ
    0.59
    ValueStyle
    0.59
    exitRule
    0.57
    nonatomic
    0.57
    years
    0.56
     Wiktionnaire
    0.56
    RTEE
    0.56
    Activations Density 0.105%

    No Known Activations