© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7080
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and their derivatives, particularly in a formal calculus context

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

    "f" followed by a mathematical expression

    np_acts-logits-general · gemini-2.0-flash

    mathematical function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     huom
    -0.42
    UrlResolution
    -0.40
    ayuno
    -0.36
    ñores
    -0.35
     Zuschauer
    -0.34
     presentes
    -0.34
     majeur
    -0.33
     történ
    -0.33
     Besonder
    -0.32
    chapper
    -0.32
    POSITIVE LOGITS
    rungsseite
    0.78
     المعيارى
    0.75
     contextLoads
    0.73
    Cyfarwyddwr
    0.70
     function
    0.67
     hàm
    0.66
    IndentedString
    0.66
    RegressionTest
    0.64
    functions
    0.61
    dafx
    0.61
    Activations Density 1.851%

    No Known Activations