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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 3144
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic conditions and trends

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

    Preceding numbers or measurements

    np_acts-logits-general · gemini-2.0-flash

    historic lows, record highs, low EQE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.73
     AssemblyTitle
    -0.67
     distanciation
    -0.66
    ⓧ
    -0.63
    󠁢
    -0.63
    addCriterion
    -0.59
     صوتيه
    -0.55
     Cientí
    -0.53
     Faso
    -0.51
     LCCN
    -0.51
    POSITIVE LOGITS
     levels
    1.00
     highs
    0.96
     niveles
    0.94
     lows
    0.86
    levels
    0.85
     niveaux
    0.83
     record
    0.79
     Levels
    0.78
     níveis
    0.77
     LEVELS
    0.76
    Activations Density 0.128%

    No Known Activations