© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6055
    Prev
    Next
    INDEX
    Explanations

    terms related to health and biological conditions

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

    before prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    organizational units

    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
    yntaxException
    -0.75
    ]))
    
    -0.67
     يتيمه
    -0.65
     estekak
    -0.63
    OGND
    -0.63
     StatelessWidget
    -0.62
    rawDesc
    -0.61
    #+#
    -0.60
    FontOfSize
    -0.59
     تضيفلها
    -0.58
    POSITIVE LOGITS
     hinweg
    0.78
     within
    0.56
    별
    0.56
     مختلف
    0.51
     tertentu
    0.51
    別の
    0.50
    Personendaten
    0.48
    別に
    0.48
    /
    0.48
    einander
    0.47
    Activations Density 1.104%

    No Known Activations