© 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. 20-GEMMASCOPE-RES-16K
    11. 15164
    Prev
    Next
    INDEX
    Explanations

    instances of changing opinions or decisions

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

    "Mind" or references to changing one's "mind"

    np_acts-logits-general · gemini-2.0-flash

    one's mind

    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
    TestingModule
    -0.48
    SpringBootTest
    -0.48
    tré
    -0.42
    viš
    -0.40
    ättern
    -0.38
    naio
    -0.38
    nato
    -0.38
    انگلیسی
    -0.38
    Fal
    -0.38
     pytest
    -0.37
    POSITIVE LOGITS
     mind
    2.99
     minds
    2.49
    mind
    2.42
     Mind
    2.29
     MIND
    2.23
    Mind
    2.18
    MIND
    1.85
     Minds
    1.79
    minds
    1.78
     minded
    1.55
    Activations Density 0.136%

    No Known Activations