© 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. 11296
    Prev
    Next
    INDEX
    Explanations

    terms related to propulsion systems and their performance

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

    Technical or mechanical processes

    np_acts-logits-general · gemini-2.0-flash

    technical concepts and their classification

    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
    Personendaten
    -0.60
    Rujuakan
    -0.55
    AndEndTag
    -0.52
     récon
    -0.52
    Hozzáférés
    -0.50
     doute
    -0.49
    RepeatedField
    -0.49
     siyang
    -0.48
    rungsseite
    -0.48
    はじめに
    -0.47
    POSITIVE LOGITS
    brainly
    0.78
    HtmlAttribute
    0.71
     SqlCommand
    0.67
    nastics
    0.64
    notag
    0.63
    )');
    0.62
    ########.
    0.62
    etheless
    0.61
    <%=
    0.60
     BoxDecoration
    0.60
    Activations Density 0.902%

    No Known Activations