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. 10831
    Prev
    Next
    INDEX
    Explanations

    instances of awakening or realization in context

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

    Follows a form of "I realize" or "to realize"

    np_acts-logits-general · gemini-2.0-flash

    coming to realize

    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
    MigrationBuilder
    -1.08
     للمعارف
    -0.73
    zzleHttp
    -0.71
    ########.
    -0.67
     ISNI
    -0.66
    principalTable
    -0.64
    CloseOperation
    -0.64
     continúas
    -0.61
     Мексичка
    -0.60
     referenties
    -0.60
    POSITIVE LOGITS
     realize
    2.33
     realization
    2.31
     realizing
    2.22
     realizes
    2.22
     realized
    2.21
     realise
    2.14
     realisation
    2.08
     realising
    2.04
     realised
    2.02
     realises
    1.98
    Activations Density 0.459%

    No Known Activations