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. 14288
    Prev
    Next
    INDEX
    Explanations

    terms related to longevity and durability in a product or situation.

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

    words related to hidden or secret information.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating duration or extended time periods.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    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
    migrationBuilder
    -0.59
    hasMoreElements
    -0.49
    ustu
    -0.48
    nsis
    -0.47
    immediately
    -0.47
     spend
    -0.46
    Immediately
    -0.46
    Aix
    -0.46
    يكب
    -0.43
    testng
    -0.43
    POSITIVE LOGITS
     longer
    2.18
    longer
    1.80
     Longer
    1.76
     longest
    1.66
    Longer
    1.62
     long
    1.47
     LONG
    1.42
     Longest
    1.40
     länger
    1.32
    longest
    1.29
    Activations Density 0.284%

    No Known Activations