© 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. 11-GEMMASCOPE-RES-16K
    6. 2101
    Prev
    Next
    INDEX
    Explanations

    structured data categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    意
    -0.58
     nakalista
    -0.50
     意
    -0.48
     stil
    -0.48
    Titled
    -0.47
    EnumMember
    -0.47
    之
    -0.46
     aapt
    -0.46
    schirm
    -0.45
     manej
    -0.45
    POSITIVE LOGITS
    Portail
    4.33
    بوابة
    3.07
    Portale
    2.58
     Portail
    1.86
    Datuak
    1.41
    GEBURTSDATUM
    1.09
    Портал
    1.04
    Portály
    1.03
     بوابة
    0.89
    expandindo
    0.80
    Activations Density 0.196%

    No Known Activations