Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14707
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to recovery and rehabilitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isDirectory
    -0.68
     Lamb
    -0.62
    InSection
    -0.62
     inst
    -0.61
    JvmStatic
    -0.60
    forums
    -0.60
     tag
    -0.57
     lamb
    -0.56
     Lam
    -0.56
     cliquant
    -0.56
    POSITIVE LOGITS
     recoveries
    1.89
     Recover
    1.86
     recovery
    1.85
     Recovery
    1.83
     recover
    1.78
    Recovery
    1.76
     RECOVERY
    1.73
     recovered
    1.66
     recovers
    1.64
    recovery
    1.61
    Activations Density 0.075%

    No Known Activations