© 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. 5057
    Prev
    Next
    INDEX
    Explanations

    phrases relating to potential and therapeutic applications, especially in the context of stem cells and their implications for treatment and human well-being

    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
    MessageTagHelper
    -0.71
    Чыганаклар
    -0.64
     AssemblyVersion
    -0.64
     recul
    -0.63
    енча
    -0.62
    ValueStyle
    -0.61
     PyTuple
    -0.59
     autorytatywna
    -0.59
     PARSER
    -0.57
    Clik
    -0.55
    POSITIVE LOGITS
     potential
    2.45
    potential
    2.22
    Potential
    2.17
     Potential
    2.16
     potentials
    2.08
     potentiel
    1.98
     POTENTIAL
    1.95
     potencial
    1.92
     potensi
    1.82
     potentialities
    1.74
    Activations Density 0.445%

    No Known Activations