© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9478
    Prev
    Next
    INDEX
    Explanations

    contextual phrases around obedience and commitment to a cause

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

    appearing before prepositions

    np_acts-logits-general · gemini-2.0-flash

    medical/biological proteins and pathways

    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
     pihaknya
    -0.68
     Grecs
    -0.65
     préc
    -0.64
     étoient
    -0.63
     normaux
    -0.63
     précédents
    -0.63
     réguli
    -0.62
     meille
    -0.62
     acestei
    -0.61
     avoient
    -0.61
    POSITIVE LOGITS
    DockStyle
    0.78
    gameserver
    0.66
     maxn
    0.66
    TextHelper
    0.64
    GenerationType
    0.64
     JpaRepository
    0.64
    therford
    0.63
     Nav
    0.61
     springfox
    0.60
    ModelAdmin
    0.60
    Activations Density 1.573%

    No Known Activations