© 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. 11-GEMMASCOPE-RES-16K
    11. 12938
    Prev
    Next
    INDEX
    Explanations

    references to calibration methods and data points in statistical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setCellStyle
    -0.50
     }^{*
    -0.46
     honor
    -0.46
     stands
    -0.45
     sortant
    -0.45
    TOP
    -0.45
     numerus
    -0.45
    execSQL
    -0.44
     Names
    -0.44
    stands
    -0.44
    POSITIVE LOGITS
    LLocation
    0.92
    NameInMap
    0.86
    windowFixed
    0.80
    AnchorStyles
    0.70
    tonsoft
    0.60
    msgTypes
    0.60
    енча
    0.58
    хьтан
    0.58
     dữ
    0.57
     empiric
    0.55
    Activations Density 1.123%

    No Known Activations