© 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. 1349
    Prev
    Next
    INDEX
    Explanations

    specific numeric values or symbols potentially related to data, evidence, or mathematical expressions

    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
     '\\;'
    -1.05
    ViewFeatures
    -1.04
    SequentialGroup
    -0.89
    PreferredItem
    -0.80
    +#+
    -0.80
    yntaxException
    -0.76
     propOrder
    -0.76
    elemField
    -0.76
     فريبيس
    -0.75
     Савезне
    -0.74
    POSITIVE LOGITS
     tantum
    0.49
    仑
    0.47
     lo
    0.46
     humaine
    0.45
    trieb
    0.45
     fiables
    0.44
     långt
    0.44
     ball
    0.43
     fiable
    0.43
     most
    0.42
    Activations Density 0.967%

    No Known Activations