© 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. 20-GEMMASCOPE-RES-16K
    11. 731
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to numerical analysis and set theory

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

    Mentions positive integers

    np_acts-logits-general · gemini-2.0-flash

    positive integers and their properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     <<<<<<<<<<<<<<
    -0.42
     Приступљено
    -0.37
    Crossref
    -0.35
     she
    -0.35
     siyah
    -0.34
     nac
    -0.32
    jScrollPane
    -0.32
     lauter
    -0.31
    )__
    -0.31
    horizontalLayout
    -0.30
    POSITIVE LOGITS
    RegressionTest
    0.59
    CppMethod
    0.57
    ItemBackground
    0.53
    cellation
    0.51
    RetentionPolicy
    0.50
    Composable
    0.50
    parsedMessage
    0.49
    édrale
    0.49
    siery
    0.49
     astore
    0.48
    Activations Density 2.250%

    No Known Activations