© 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. 15978
    Prev
    Next
    INDEX
    Explanations

    references to medical-related terms and concepts

    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
    DebuggerNonUser
    -1.11
     LoggerFactory
    -0.99
    SBATCH
    -0.84
    Enllaces
    -0.76
     Efq
    -0.76
    IntoConstraints
    -0.75
    UnitTesting
    -0.73
     يتيمه
    -0.72
     Szcz
    -0.71
     Ips
    -0.70
    POSITIVE LOGITS
     Med
    2.94
    Med
    2.80
    med
    2.54
     med
    2.51
     MED
    2.48
    MED
    2.19
     medi
    1.74
    medi
    1.70
     Medi
    1.63
    Medi
    1.62
    Activations Density 0.113%

    No Known Activations