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

    Neuronpedia

    Jacobian LensNEW
    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. 6835
    Prev
    Next
    INDEX
    Explanations

    references to physical structures and configurations

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

    "Arranged" or similar words like "spaced" and "grouped"

    np_acts-logits-general · gemini-2.0-flash

    arranged spatially

    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
    ()};
    -0.47
    мол
    -0.45
    ahal
    -0.44
    κτή
    -0.43
    }};
    -0.43
    näm
    -0.43
    }$)
    -0.43
     }}"></
    -0.42
    ZZO
    -0.42
     conclusão
    -0.42
    POSITIVE LOGITS
     arranged
    1.50
    arranged
    1.33
     spaced
    1.32
     Arranged
    1.26
     grouped
    1.17
     arrange
    1.14
     arranges
    1.11
    spaced
    1.10
     stacked
    1.06
     staggered
    1.06
    Activations Density 1.038%

    No Known Activations