Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8508
    Prev
    Next
    INDEX
    Explanations

    terms related to extreme conditions in material science or engineering, particularly those associated with lubrication and chemical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOPQRST
    -0.73
    */),
    -0.63
    ]")]
    -0.61
    ">//
    -0.60
     AssemblyCulture
    -0.59
     @"/
    -0.59
     <=",
    -0.58
     Lightboxes
    -0.56
    classnames
    -0.55
    Twas
    -0.55
    POSITIVE LOGITS
    省市镇
    0.71
     trajets
    0.67
    CloseOperation
    0.66
     useParams
    0.61
    HomeAsUpEnabled
    0.61
     rospy
    0.57
     useNavigate
    0.56
    StoryboardSegue
    0.56
    بوابة
    0.55
    WebServlet
    0.54
    Activations Density 14.546%

    No Known Activations