© 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. 18-GEMMASCOPE-RES-16K
    11. 874
    Prev
    Next
    INDEX
    Explanations

    concepts related to capacity, capability, and performance attributes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    capacity and capability

    np_acts-logits-general · gemini-2.0-flash

    capacity and capability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.64
    griffen
    -0.63
    contentLoaded
    -0.54
    Itoa
    -0.52
     Mär
    -0.50
    ناية
    -0.48
     nakalista
    -0.48
    gouv
    -0.48
     useSelector
    -0.47
    مراجع
    -0.47
    POSITIVE LOGITS
     capacity
    2.33
     capability
    2.22
     capabilities
    2.17
     capacities
    2.00
     Capacity
    1.96
    capacity
    1.94
     Capabilities
    1.89
    Capacity
    1.83
     Capability
    1.81
     capable
    1.80
    Activations Density 0.359%

    No Known Activations