© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3483
    Prev
    Next
    INDEX
    Explanations

    terms related to planning and strategy development in a healthcare or financial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.50
    чество
    -0.43
    BorderFactory
    -0.43
     invitamos
    -0.42
     resourceCulture
    -0.42
    antd
    -0.42
    posia
    -0.42
     internetowa
    -0.41
    érrez
    -0.41
     thuộc
    -0.40
    POSITIVE LOGITS
     plan
    3.00
     plans
    2.70
     Plan
    2.61
    plan
    2.58
     PLAN
    2.45
     Plans
    2.44
    Plan
    2.44
    plans
    2.37
    Plans
    2.27
    PLAN
    2.27
    Activations Density 0.316%

    No Known Activations