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. 2104
    Prev
    Next
    INDEX
    Explanations

    references to childhood experiences and memories

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

    youth or childhood

    np_acts-logits-general · gemini-2.0-flash

    childhood and youth

    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
    MENAFN
    -0.61
     ModelExpression
    -0.51
    eschön
    -0.50
    ians
    -0.46
     estekak
    -0.46
    jsxFileName
    -0.45
    räck
    -0.44
    AddTagHelper
    -0.43
    esson
    -0.42
     esc
    -0.42
    POSITIVE LOGITS
     child
    1.24
     young
    1.23
     younger
    1.19
    child
    1.18
     youth
    1.09
     kid
    1.08
     youngster
    1.08
    young
    1.04
     childhood
    1.01
    youth
    0.99
    Activations Density 0.155%

    No Known Activations