Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 13583
    Prev
    Next
    INDEX
    Explanations

    topics related to societal and cultural dynamics

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

    Follows "world," "era," "culture," "context", or "year."

    np_acts-logits-general · gemini-2.0-flash

    describing a world defined by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.56
    äsent
    -0.56
     câte
    -0.53
    äfts
    -0.52
    fromnode
    -0.50
    astify
    -0.49
     tallest
    -0.49
    󠁢
    -0.48
    appearing
    -0.48
    brainly
    -0.47
    POSITIVE LOGITS
     characterized
    1.13
     filled
    1.13
     devoid
    1.06
     focused
    1.02
     dedicated
    1.01
     committed
    0.99
     driven
    0.98
     dominated
    0.97
     characterised
    0.97
     fueled
    0.96
    Activations Density 0.368%

    No Known Activations