© 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. 25-GEMMASCOPE-RES-16K
    11. 7534
    Prev
    Next
    INDEX
    Explanations

    numerical representations or references that quantify specific information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himſelf
    -0.85
     myſelf
    -0.79
     raiſ
    -0.78
     themſelves
    -0.76
     purpoſe
    -0.72
     ſmall
    -0.72
     defaultstate
    -0.70
     tranſ
    -0.69
     itſelf
    -0.69
     ſtate
    -0.69
    POSITIVE LOGITS
    7
    1.03
    9
    1.02
    5
    1.02
    6
    1.01
    8
    1.00
    4
    0.99
    3
    0.96
    0
    0.93
    2
    0.91
    1
    0.89
    Activations Density 1.446%

    No Known Activations