© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 1607
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate overall statements or summaries related to discussions or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InSection
    -0.80
    getDoctrine
    -0.75
    出版年
    -0.74
    mappedBy
    -0.73
    ništvo
    -0.70
    oplayer
    -0.68
    Kontrola
    -0.67
    onomy
    -0.67
    AndEndTag
    -0.67
    onAttach
    -0.67
    POSITIVE LOGITS
    RegressionTest
    0.68
    UnusedPrivate
    0.64
    ↵↵
    0.58
     CreateTagHelper
    0.51
    LookAnd
    0.51
    ↵
    0.50
    TypedDataSet
    0.48
    PageModule
    0.47
    AutoScaleMode
    0.46
     TestBed
    0.45
    Activations Density 2.587%

    No Known Activations