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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 5121
    Prev
    Next
    INDEX
    Explanations

    references to practices or actions in societal or professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.86
     Ked
    -0.84
    RectangleBorder
    -0.80
    SBATCH
    -0.78
    ngOnInit
    -0.77
    quelles
    -0.76
    ghans
    -0.75
    InputBorder
    -0.75
     препратки
    -0.74
    höhung
    -0.74
    POSITIVE LOGITS
     practice
    2.16
     practices
    2.11
     Practice
    1.98
     PRACTICE
    1.92
    Practice
    1.90
     Practices
    1.89
    PRACTICE
    1.83
    practice
    1.77
     practise
    1.76
    Practices
    1.71
    Activations Density 0.049%

    No Known Activations