© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3856
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical expressions and symbols

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

    equivalence or equality

    np_acts-logits-general · gemini-2.0-flash

    is equal, equivalent, precisely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.65
    DockStyle
    -0.64
     propOrder
    -0.63
    yntaxException
    -0.63
     незавершена
    -0.61
     defaultstate
    -0.59
    BufferException
    -0.58
    writeField
    -0.58
    webElementXpaths
    -0.57
     arşivlendi
    -0.57
    POSITIVE LOGITS
     equivalent
    0.56
     exactly
    0.55
     identical
    0.52
     always
    0.49
     perfectly
    0.48
     indeed
    0.45
     equal
    0.44
     easily
    0.44
     easy
    0.42
     perfect
    0.42
    Activations Density 2.507%

    No Known Activations