© 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. 24-GEMMASCOPE-RES-16K
    11. 2825
    Prev
    Next
    INDEX
    Explanations

    phrases related to consideration and application

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

    Preceding "mind"

    np_acts-logits-general · gemini-2.0-flash

    keeping in mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.60
    TestingModule
    -0.51
    annica
    -0.51
    lamabad
    -0.47
    weetened
    -0.46
     prawda
    -0.45
     faute
    -0.45
    lossus
    -0.43
    orkan
    -0.43
     Stem
    -0.43
    POSITIVE LOGITS
     mind
    3.27
    mind
    2.52
     Mind
    2.38
    Mind
    2.30
     MIND
    2.28
     minds
    2.26
    MIND
    1.92
     mente
    1.75
    minds
    1.62
     minde
    1.57
    Activations Density 0.166%

    No Known Activations