© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13218
    Prev
    Next
    INDEX
    Explanations

    operations related to data structures and their manipulations

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

    Method calls using `.get` and `.put`

    np_acts-logits-general · gemini-2.0-flash

    mapping and collection methods

    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
    ագրություններ
    -0.73
    اریخ
    -0.65
     HasFactory
    -0.61
     Wickham
    -0.61
     thiệu
    -0.57
    DialogContent
    -0.56
    ביוגרפיה
    -0.54
    ➟
    -0.54
     die
    -0.53
    guten
    -0.53
    POSITIVE LOGITS
    put
    1.02
     put
    0.84
    Put
    0.83
     Put
    0.79
     PUT
    0.76
    putting
    0.68
     puts
    0.68
    Putting
    0.68
    PUT
    0.68
     putting
    0.67
    Activations Density 0.098%

    No Known Activations