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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4110
    Prev
    Next
    INDEX
    Explanations

    mentions of funding and financial support within structural changes or community programs

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

    Business or institution shutdowns

    np_acts-logits-general · gemini-2.0-flash

    closing, shutting, and abandonment

    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
    ">+
    -0.63
    +#+
    -0.55
    tvguidetime
    -0.54
    Демографія
    -0.54
     betweenstory
    -0.52
    NavigationView
    -0.51
    epresidente
    -0.50
     jspb
    -0.50
    makeConstraints
    -0.50
     createState
    -0.47
    POSITIVE LOGITS
     closure
    1.53
     closing
    1.33
     closures
    1.33
     Closure
    1.30
     shutting
    1.29
    Closure
    1.19
    closure
    1.19
     decommission
    1.18
     ceasing
    1.18
     discontin
    1.18
    Activations Density 0.505%

    No Known Activations