© 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. 6127
    Prev
    Next
    INDEX
    Explanations

    keywords related to education and learning

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

    Learning more about something

    np_acts-logits-general · gemini-2.0-flash

    learn more about

    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
    Bioaccumulative
    -0.75
     tartalomajánló
    -0.65
    ніципа
    -0.64
    Portail
    -0.61
    CodedInputStream
    -0.59
    BorderFactory
    -0.58
     ModelExpression
    -0.56
     resourceCulture
    -0.56
    GEBURTSDATUM
    -0.55
    UnusedPrivate
    -0.54
    POSITIVE LOGITS
     about
    1.51
     more
    1.29
    about
    1.06
    About
    0.94
     details
    0.94
     ABOUT
    0.93
     how
    0.93
     mehr
    0.92
    more
    0.91
     tungkol
    0.90
    Activations Density 0.161%

    No Known Activations