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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 58750
    Prev
    Next
    INDEX
    Explanations

    references to authority figures and the concept of worship

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

    worldly pursuits and worship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     intervene
    -0.36
     península
    -0.36
     Anexo
    -0.36
    StateToProps
    -0.36
    zzleHttp
    -0.36
    Filmografie
    -0.35
     tweeting
    -0.35
    ViewImports
    -0.34
    :+:
    -0.34
    Morfo
    -0.34
    POSITIVE LOGITS
    IUrlHelper
    0.49
    FieldDescriptor
    0.42
     fashions
    0.41
    CodeAttribute
    0.40
     kasarigan
    0.40
    müş
    0.40
     femininos
    0.40
     OMITBAD
    0.39
    RegistryLite
    0.39
    Klu
    0.39
    Activations Density 0.028%

    No Known Activations