© 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. 25-GEMMASCOPE-RES-16K
    11. 13962
    Prev
    Next
    INDEX
    Explanations

    technical terms related to circuit design and operation

    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
    !’
    -0.69
     typelib
    -0.65
    enumi
    -0.61
     \"
    -0.58
    !&
    -0.58
    !«
    -0.58
     `/
    -0.57
    !*
    -0.57
     !”
    -0.57
    !'
    -0.56
    POSITIVE LOGITS
     US
    1.37
    US
    1.10
     plurality
    1.06
     thereto
    1.01
     FIG
    0.98
     therefrom
    0.98
     Preferably
    0.93
     embodiments
    0.92
     thereof
    0.92
    FIG
    0.90
    Activations Density 2.402%

    No Known Activations