© 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. 10-GEMMASCOPE-RES-16K
    6. 12339
    Prev
    Next
    INDEX
    Explanations

    the beginning of new paragraphs or sections in a text context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.56
     CWE
    -0.55
    WebVitals
    -0.54
     credere
    -0.52
    "]),
    -0.51
     snippetHide
    -0.51
    basicConfig
    -0.50
     sociais
    -0.48
     formales
    -0.47
    djangoproject
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.91
    ValueStyle
    0.72
     also
    0.68
     anybody
    0.66
     تضيفلها
    0.62
     San
    0.61
     anyone
    0.58
    Density
    0.56
    anganese
    0.56
     чле
    0.56
    Activations Density 0.363%

    No Known Activations