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. 8187
    Prev
    Next
    INDEX
    Explanations

    past experiences and personal anecdotes related to growth and learning

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

    Following "was" and related to youth

    np_acts-logits-general · gemini-2.0-flash

    when was younger or growing

    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
    AddTagHelper
    -0.76
    Selanjutnya
    -0.57
    ContentAsync
    -0.57
    PMailer
    -0.56
    原始内容存档于
    -0.56
     continúas
    -0.56
     ModelExpression
    -0.54
    льевич
    -0.51
     springfox
    -0.51
    rungsseite
    -0.50
    POSITIVE LOGITS
     younger
    1.01
     young
    0.98
    young
    0.83
     little
    0.82
     joven
    0.73
     liten
    0.71
    little
    0.70
     growing
    0.69
     Younger
    0.69
     kecil
    0.67
    Activations Density 0.128%

    No Known Activations