© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10258
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts relevant to algorithms and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -0.86
    2
    -0.80
    ecore
    -0.73
    1
    -0.71
    stalline
    -0.71
    Portale
    -0.64
    ίου
    -0.63
     m
    -0.63
    dew
    -0.62
    ########.
    -0.62
    POSITIVE LOGITS
    ſelf
    1.52
     itſelf
    1.50
     himſelf
    1.45
    ſelves
    1.41
     myſelf
    1.41
     raiſ
    1.40
     themſelves
    1.38
     Efq
    1.33
     occaf
    1.31
     doubtnut
    1.29
    Activations Density 1.023%

    No Known Activations