© 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. 14308
    Prev
    Next
    INDEX
    Explanations

    specific technical or digital attributes related to hardware

    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
     Ca
    -1.76
    Ca
    -1.68
     CA
    -1.65
    ca
    -1.60
    CA
    -1.56
     ca
    -1.53
     CAP
    -1.52
    CAP
    -1.51
     Cap
    -1.49
     cap
    -1.47
    POSITIVE LOGITS
     Cr
    0.62
     cr
    0.59
    DockStyle
    0.58
     CR
    0.57
     Cor
    0.56
    cr
    0.55
     Crist
    0.54
    Cor
    0.54
    Cr
    0.52
    CR
    0.51
    Activations Density 2.298%

    No Known Activations