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-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 130019
    Prev
    Next
    INDEX
    Explanations

    references to marriage and temple-related beliefs in a religious context

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

    temple sealings eternal families

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.50
    OGND
    -0.49
     HttpNotFound
    -0.49
     kiệm
    -0.48
     Winaray
    -0.47
    yarnpkg
    -0.46
    دانشنامهٔ
    -0.46
     hunch
    -0.44
    expertise
    -0.44
    Brainz
    -0.44
    POSITIVE LOGITS
    ReusableCell
    0.38
     Celery
    0.38
     Celestial
    0.35
     celery
    0.34
     vivas
    0.34
    Cel
    0.33
    éez
    0.32
     دیکھیے
    0.32
     hotell
    0.32
    oredCriteria
    0.32
    Activations Density 0.055%

    No Known Activations