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

    Neuronpedia

    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. 3-GEMMASCOPE-RES-16K
    11. 8826
    Prev
    Next
    INDEX
    Explanations

    specific citation formats and punctuation in academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dei
    -0.55
     casa
    -0.53
     pia
    -0.53
    piac
    -0.51
     model
    -0.49
    rae
    -0.48
     board
    -0.48
    nai
    -0.47
    esu
    -0.47
    佩
    -0.45
    POSITIVE LOGITS
     Jefus
    0.90
    RegressionTest
    0.89
    PerformLayout
    0.88
    awtextra
    0.86
     fhort
    0.86
     purpoſe
    0.86
    WithIOException
    0.85
     pleaſure
    0.85
    Rhestr
    0.84
     himſelf
    0.82
    Activations Density 1.308%

    No Known Activations