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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12605
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and data types

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

    Code, memory, or academic publication references

    np_acts-logits-general · gemini-2.0-flash

    byte array, fragment array

    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
     متعلقه
    -0.58
    είς
    -0.57
    SourceChecksum
    -0.52
     CCPA
    -0.50
    mybatisplus
    -0.49
    pren
    -0.49
     Curie
    -0.49
    ldern
    -0.48
    ondi
    -0.48
    chede
    -0.48
    POSITIVE LOGITS
     monasterio
    0.54
     دریافت‌شده
    0.53
     religieuses
    0.53
    Hochspringen
    0.53
     JpaRepository
    0.52
    IUrlHelper
    0.52
     createState
    0.52
    elemField
    0.51
     femininas
    0.51
    URLException
    0.51
    Activations Density 0.262%

    No Known Activations