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. 12-GEMMASCOPE-RES-16K
    6. 14481
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions affecting the lungs and their associated treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Izvori
    -0.60
    kommer
    -0.52
     &___
    -0.51
     ModelExpression
    -0.49
    ต่าง
    -0.48
     évidence
    -0.48
     stubble
    -0.48
    SuccessListener
    -0.47
     milagro
    -0.47
    out
    -0.46
    POSITIVE LOGITS
    TagHelper
    0.74
    queryInterface
    0.70
     BoxFit
    0.68
    Empereur
    0.67
    ExtendWith
    0.66
    reactstrap
    0.64
    ophageal
    0.63
    )"),
    0.62
    hdessä
    0.62
    LookAnd
    0.62
    Activations Density 0.671%

    No Known Activations