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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5572
    Prev
    Next
    INDEX
    Explanations

    the presence of the token "<bos>", indicating the beginning of a document or section

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

    Code snippets or HTML table formatting

    np_acts-logits-general · gemini-2.0-flash

    programming and web development

    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
    ̍t
    -0.66
    --)
    
    -0.63
    onOptions
    -0.62
    Зноскі
    -0.61
    basicConfig
    -0.60
    InjectMocks
    -0.57
     صوتيه
    -0.57
    хьтан
    -0.56
    WebElementEntity
    -0.56
    tvguidetime
    -0.56
    POSITIVE LOGITS
    <th>
    0.69
    <tr>
    0.61
    ="@+
    0.53
    \}\\
    0.52
    }{|
    0.50
     cuc
    0.49
    roof
    0.46
     colspan
    0.46
     {{{
    0.46
     UIAlert
    0.45
    Activations Density 0.041%

    No Known Activations