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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1027
    Prev
    Next
    INDEX
    Explanations

    references to mental health issues and challenges

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

    references to psychological trauma and emotional struggles

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

    dealing with difficulties

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Bronnen
    -0.66
    cloudfront
    -0.62
    UserScript
    -0.54
     naman
    -0.54
    cdef
    -0.53
    ansha
    -0.52
    antMatchers
    -0.52
     समीक्षाएं
    -0.52
     yii
    -0.51
    ண்டும்
    -0.51
    POSITIVE LOGITS
     dealing
    1.60
     Dealing
    1.46
    Dealing
    1.40
     struggle
    1.39
     coping
    1.38
     struggling
    1.36
     grappling
    1.35
     deal
    1.32
    dealing
    1.29
     cope
    1.26
    Activations Density 0.202%

    No Known Activations