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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10352
    Prev
    Next
    INDEX
    Explanations

    sentences expressing personal opinions or experiences

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

    "I" followed by a verb or auxiliary verb

    np_acts-logits-general · gemini-2.0-flash

    personal assertions and beliefs

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ditto
    -0.73
    Demikian
    -0.69
    Herzliche
    -0.67
     occasioned
    -0.63
    Ditto
    -0.60
    Gruß
    -0.59
     Ditto
    -0.58
    ところが
    -0.57
     lousy
    -0.57
    pernic
    -0.57
    POSITIVE LOGITS
     насељу
    0.77
     honestly
    0.76
    klart
    0.68
     definitely
    0.67
     literalmente
    0.64
     correctes
    0.64
     ofc
    0.63
     definitivamente
    0.62
     internally
    0.61
    honestly
    0.60
    Activations Density 0.214%

    No Known Activations