© 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. 2-GEMMASCOPE-RES-16K
    11. 1323
    Prev
    Next
    INDEX
    Explanations

    references to significant or defining elements in narratives or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Which
    -0.61
     Which
    -0.61
     Оно
    -0.49
     XNUMX
    -0.48
    dike
    -0.47
    腕
    -0.47
    ivka
    -0.47
     bril
    -0.46
    λαμβ
    -0.45
    andte
    -0.44
    POSITIVE LOGITS
    featureID
    0.92
    OGND
    0.91
     disambiguazione
    0.82
    Хьажоргаш
    0.79
     AssemblyTitle
    0.79
    RTEE
    0.76
    LookAnd
    0.75
     daß
    0.73
    TypedDataSet
    0.73
     propOrder
    0.73
    Activations Density 0.197%

    No Known Activations