© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10864
    Prev
    Next
    INDEX
    Explanations

    numerical values related to concentrations or measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.87
     kiệm
    -0.82
    原始内容存档于
    -0.78
     Eilish
    -0.75
    CppCodeGen
    -0.73
    iedene
    -0.73
     Janis
    -0.70
    Personendaten
    -0.70
     womb
    -0.69
     Pekan
    -0.68
    POSITIVE LOGITS
    QtWidgets
    0.61
    ukone
    0.57
    ‰
    0.55
    <0xE2>
    0.55
    adag
    0.55
    baga
    0.54
     Ло
    0.53
    fortawesome
    0.52
    uoco
    0.52
    aga
    0.52
    Activations Density 0.248%

    No Known Activations