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. 1210
    Prev
    Next
    INDEX
    Explanations

    programming syntax and punctuation characters

    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
     Roskov
    -0.77
    ніципалі
    -0.77
     linkovi
    -0.73
    Personensuche
    -0.73
    Datuak
    -0.71
     <=",
    -0.67
    ///</
    -0.66
    elemField
    -0.66
     '{@
    -0.65
    webElementXpaths
    -0.64
    POSITIVE LOGITS
    awtextra
    0.53
    PerformLayout
    0.53
    URERS
    0.52
    enumi
    0.50
    consulté
    0.49
    NOWLEDG
    0.47
    олові
    0.47
    unre
    0.47
     :(
    0.47
     না
    0.47
    Activations Density 0.069%

    No Known Activations