© 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. 1729
    Prev
    Next
    INDEX
    Explanations

    names and titles, particularly those related to individuals and their roles or positions

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

    Arabic or Persian text/names mixed with transliterated text

    np_acts-logits-general · gemini-2.0-flash

    Arab levies and troops

    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
     
    -0.55
     two
    -0.54
     venuto
    -0.46
    끊
    -0.43
     i
    -0.43
    two
    -0.42
     I
    -0.42
     पास
    -0.42
    গ্রহ
    -0.42
    j
    -0.41
    POSITIVE LOGITS
     autorytatywna
    1.41
     مشين
    1.13
     мәкал
    0.96
    IUrlHelper
    0.94
    +#+#
    0.89
     MessageBoxIcon
    0.85
    Autoritní
    0.85
    Vidite
    0.85
    IntoConstraints
    0.84
     gyhoeddwyd
    0.82
    Activations Density 0.023%

    No Known Activations