© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 390
    Prev
    Next
    INDEX
    Explanations

    references to the largest entities or groups in various categories

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

    Follows superlative adjectives

    np_acts-logits-general · gemini-2.0-flash

    superlatives followed by specific nouns

    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
     rempliss
    -0.52
     habile
    -0.51
     politiker
    -0.50
     ecco
    -0.47
    važ
    -0.47
     emergencia
    -0.47
    hadiran
    -0.46
     مشين
    -0.46
     Colleagues
    -0.46
    ામ
    -0.45
    POSITIVE LOGITS
     single
    0.81
     незавершена
    0.71
     non
    0.68
    Portály
    0.66
    single
    0.66
     autorytatywna
    0.65
     lenker
    0.64
     ever
    0.63
    Portail
    0.63
     active
    0.63
    Activations Density 0.217%

    No Known Activations