© 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. 4-GEMMASCOPE-RES-16K
    6. 10735
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols often used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.59
    glLoadIdentity
    -0.58
    Hentet
    -0.58
    </tfoot>
    -0.55
     >=",
    -0.55
    UnusedPrivate
    -0.53
    )|^{
    -0.51
    arque
    -0.50
    iarkan
    -0.50
    }}">
    -0.48
    POSITIVE LOGITS
     anesthetic
    0.62
     intptr
    0.62
     ←
    0.62
    ※
    0.58
    ImageContext
    0.58
     Martyr
    0.58
     <--
    0.58
     tfsi
    0.58
     tolu
    0.58
     Anſ
    0.56
    Activations Density 0.857%

    No Known Activations