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

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 9363
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SMR
    -0.46
    ModelSerializer
    -0.43
    PED
    -0.39
     Up
    -0.38
    ...
    -0.38
     sav
    -0.37
     ly
    -0.37
    кие
    -0.37
     permita
    -0.37
    期的
    -0.37
    POSITIVE LOGITS
    SourceChecksum
    0.84
     myſelf
    0.81
     createSprite
    0.81
     nakalista
    0.80
    ьаж
    0.79
    onViewCreated
    0.78
     XCTest
    0.75
     Efq
    0.75
     HasFactory
    0.74
    Geplaatst
    0.74
    Activations Density 0.193%

    No Known Activations