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. 18-GEMMASCOPE-RES-16K
    6. 726
    Prev
    Next
    INDEX
    Explanations

    references to religious artifacts and rituals

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

    Follows "the" or a preposition

    np_acts-logits-general · gemini-2.0-flash

    good news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.48
     surla
    -0.43
     
    -0.41
    ,
    -0.39
    -
    -0.39
     is
    -0.39
     after
    -0.39
    ies
    -0.38
     on
    -0.38
     Dr
    -0.38
    POSITIVE LOGITS
     AssemblyProduct
    0.96
    PreferredItem
    0.92
    хьтан
    0.90
    twimg
    0.89
     auffi
    0.89
     ſind
    0.87
    hassee
    0.85
     ſever
    0.83
    expandindo
    0.83
     تانيه
    0.83
    Activations Density 0.063%

    No Known Activations