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. 1077
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of awareness or absence of something

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

    expressions of absence or loss

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

    lack of knowledge or realization

    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
     Chriftian
    -0.79
     ſtate
    -0.79
     Monfieur
    -0.77
     ſtre
    -0.77
     mergeFrom
    -0.76
     juſ
    -0.75
     Majefty
    -0.74
     Houſe
    -0.73
    archiviato
    -0.73
     pleaſure
    -0.73
    POSITIVE LOGITS
     knowledge
    1.17
    knowledge
    1.01
     Knowledge
    0.99
    Knowledge
    0.96
     know
    0.93
     knowing
    0.92
     Know
    0.91
     KNOWLEDGE
    0.87
     Wissen
    0.84
     even
    0.84
    Activations Density 0.093%

    No Known Activations