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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 12932
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to systems and processes involving transfer and transformation of energy or materials

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

    Movement/transport of substances or energy

    np_acts-logits-general · gemini-2.0-flash

    transfer of fluids, energy, or signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    InitVars
    -0.69
    IsMutable
    -0.63
    CppMethod
    -0.61
     ويكيپيديا
    -0.60
    mybatisplus
    -0.57
    enschappelijke
    -0.55
     ویکی‌پدیا
    -0.54
     JpaRepository
    -0.53
     يتيمه
    -0.53
    POSITIVE LOGITS
     electricity
    0.92
     signals
    0.88
     electrons
    0.87
     nutrients
    0.86
     fluids
    0.85
     energy
    0.83
     juice
    0.83
     juices
    0.82
     moisture
    0.78
     photons
    0.78
    Activations Density 1.016%

    No Known Activations