© 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. 22-GEMMASCOPE-RES-16K
    11. 8611
    Prev
    Next
    INDEX
    Explanations

    complexity and challenges in various contexts

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

    "So [adjective] that" construction

    np_acts-logits-general · gemini-2.0-flash

    so [adjective] that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.66
    RefNanny
    -0.62
    الإنجليزية
    -0.61
     bastante
    -0.59
     plenty
    -0.58
     suficientemente
    -0.56
    RTGC
    -0.56
    IsMutable
    -0.56
    WebElementEntity
    -0.55
     abbastanza
    -0.55
    POSITIVE LOGITS
     înc
    1.22
     it
    0.72
     that
    0.71
     you
    0.67
     sehingga
    0.62
     zelfs
    0.62
     Pourtant
    0.60
     even
    0.60
     compared
    0.60
     nobody
    0.59
    Activations Density 0.101%

    No Known Activations