© 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. 20-GEMMASCOPE-RES-16K
    11. 7814
    Prev
    Next
    INDEX
    Explanations

    references to parental responsibilities and online registration processes

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

    online services or configurations

    np_acts-logits-general · gemini-2.0-flash

    online access or electronic registration

    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
     resourceCulture
    -0.63
     TextAppearance
    -0.60
    úgó
    -0.60
    apimachinery
    -0.59
     Gambar
    -0.57
    +#+
    -0.57
    XtraEditors
    -0.56
     Giveaway
    -0.54
    RectangleBorder
    -0.54
     InputDecoration
    -0.52
    POSITIVE LOGITS
     online
    1.85
     Online
    1.66
    online
    1.63
    Online
    1.61
     ONLINE
    1.57
    ONLINE
    1.44
     electronically
    1.23
     онлайн
    1.21
     portal
    1.08
     elektron
    1.08
    Activations Density 0.223%

    No Known Activations