Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4376
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or phone number formats

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

    Numbers starting with 0 or + followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    Omaha Days

    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
    клопе
    -0.73
     gawas
    -0.68
     dietro
    -0.58
    mybatisplus
    -0.54
    hasMoreElements
    -0.54
     behind
    -0.54
    SpringBootTest
    -0.53
    achter
    -0.51
    tvguidetime
    -0.51
     Bourgoin
    -0.51
    POSITIVE LOGITS
     yii
    0.52
    setViewportView
    0.47
     SYSTEMS
    0.43
     telefono
    0.43
    Melan
    0.43
     neta
    0.43
     yyr
    0.43
    MessageTagHelper
    0.43
    システム
    0.43
     systèmes
    0.43
    Activations Density 0.127%

    No Known Activations