© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13514
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands or formatting elements

    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
     Chry
    -0.55
    AsUp
    -0.54
    eddah
    -0.53
    uestos
    -0.50
    ite
    -0.50
     zin
    -0.49
     Chbosky
    -0.49
    χν
    -0.48
     legen
    -0.46
    setViewName
    -0.45
    POSITIVE LOGITS
    ValueStyle
    1.16
    ConstraintMaker
    0.96
    tagHelperRunner
    0.85
    <sup>
    0.81
    BagLayout
    0.81
    InSection
    0.80
     disambiguazione
    0.79
    BeginContext
    0.77
    enumii
    0.75
     оригіналу
    0.75
    Activations Density 0.006%

    No Known Activations