© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7712
    Prev
    Next
    INDEX
    Explanations

    technical terms and results related to biological processes, particularly in genetic research

    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
     Abhishek
    -0.96
     Moray
    -0.83
     AB
    -0.74
     Bel
    -0.73
     Fleming
    -0.73
     Highland
    -0.71
     Silver
    -0.70
    AB
    -0.69
     McKin
    -0.69
     Abhi
    -0.68
    POSITIVE LOGITS
     Yang
    1.16
    Yang
    1.05
     Amy
    0.88
     APA
    0.83
    Amy
    0.81
     YANG
    0.81
     Neuron
    0.80
     neuron
    0.80
    neuron
    0.79
    杨
    0.76
    Activations Density 1.752%

    No Known Activations