© 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. 3-GEMMASCOPE-RES-16K
    11. 5938
    Prev
    Next
    INDEX
    Explanations

    terms related to renovation and rehabilitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.67
    ectl
    -0.58
     Schme
    -0.51
     المعيارى
    -0.48
     kaarangay
    -0.47
    acterial
    -0.46
     chia
    -0.46
     ч
    -0.45
     weiterer
    -0.45
    $_['
    -0.45
    POSITIVE LOGITS
     renovation
    1.57
     renovate
    1.49
    Renov
    1.48
     renovating
    1.44
     renovated
    1.44
     refurb
    1.43
     refurbishment
    1.40
     Renov
    1.40
     renov
    1.38
     renovations
    1.32
    Activations Density 0.184%

    No Known Activations