© 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. 17-GEMMASCOPE-RES-16K
    11. 4915
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of collecting and the concept of collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.90
    Зноскі
    -0.90
    bleshooting
    -0.89
     AssemblyCulture
    -0.88
    UseVisualStyle
    -0.88
    complexContent
    -0.87
     بيها
    -0.86
    roughs
    -0.83
    ValueStyle
    -0.83
    IBar
    -0.81
    POSITIVE LOGITS
     collections
    1.04
    COLLECT
    1.01
     Collections
    0.99
     COLLECT
    0.96
     collectors
    0.96
    Collections
    0.94
    Collectors
    0.93
     collection
    0.91
     Collect
    0.91
    Collect
    0.90
    Activations Density 0.100%

    No Known Activations