© 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. 12027
    Prev
    Next
    INDEX
    Explanations

    concepts related to economic and ethical concerns

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

    influence, control, or potential

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by dominance/outcome

    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
    errHandler
    -0.47
    هل
    -0.45
     JADX
    -0.45
    GroupLayout
    -0.44
    ăț
    -0.43
     pat
    -0.40
    ouches
    -0.40
    فحة
    -0.39
     ***!
    -0.39
     Azt
    -0.39
    POSITIVE LOGITS
     prevail
    1.30
     prevails
    1.30
     predominate
    1.29
     supersede
    1.20
     trumps
    1.18
     prevailed
    1.18
     overrides
    1.17
     triumph
    1.16
     trump
    1.14
     dominates
    1.13
    Activations Density 0.456%

    No Known Activations