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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14644
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating and following structured plans or strategies

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

    followed by "plan"

    np_acts-logits-general · gemini-2.0-flash

    plan or strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    érrez
    -0.47
    atchi
    -0.45
    ędzy
    -0.43
    ativistic
    -0.42
    нент
    -0.41
    postIndex
    -0.40
     corren
    -0.39
    enderror
    -0.37
     verg
    -0.37
     internetowa
    -0.36
    POSITIVE LOGITS
     plan
    3.33
     plans
    3.13
     Plan
    2.90
    plan
    2.88
     Plans
    2.82
    plans
    2.76
    Plan
    2.74
     PLAN
    2.72
    Plans
    2.67
     PLANS
    2.54
    Activations Density 0.308%

    No Known Activations