© 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. 6637
    Prev
    Next
    INDEX
    Explanations

    biological terms and concepts related to molecular structures and functions within tumor cells

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

    preceding numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    direct photoregulated transcription

    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
    ⍺
    -0.73
     impactful
    -0.69
     microbiome
    -0.66
    الإنجليزية
    -0.65
    ˂
    -0.64
     CRISPR
    -0.64
    ֯
    -0.62
    ˃
    -0.62
    GenerationType
    -0.61
    apunov
    -0.60
    POSITIVE LOGITS
     daß
    0.85
     läßt
    0.56
    @[+][
    0.54
    IDENCE
    0.54
     cloned
    0.53
     muß
    0.53
    లాలు
    0.52
    faßt
    0.52
     Daß
    0.51
     preparations
    0.49
    Activations Density 3.102%

    No Known Activations