© 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. 11453
    Prev
    Next
    INDEX
    Explanations

    expressions related to problem-solving or figuring things out

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

    "figure"

    np_acts-logits-general · gemini-2.0-flash

    figure out and diagram references

    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
     virtuales
    -0.63
    RegistryLite
    -0.55
     Xander
    -0.54
    anueva
    -0.54
     donnée
    -0.54
    RTGC
    -0.54
     Arjuna
    -0.52
    Jaz
    -0.52
    abetes
    -0.52
    sunami
    -0.52
    POSITIVE LOGITS
     Figures
    1.18
     Figure
    1.18
     figure
    1.17
     figures
    1.13
     figured
    1.12
     FIGURE
    1.05
    Figures
    1.02
    Figure
    1.02
     FIGURES
    0.98
     figuring
    0.97
    Activations Density 0.105%

    No Known Activations