© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8395
    Prev
    Next
    INDEX
    Explanations

    references to leadership and organizational roles within a healthcare context

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

    Follows a full stop (period)

    np_acts-logits-general · gemini-2.0-flash

    density, ankle valgus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     etc
    -0.63
     Privacidade
    -0.62
    InputBorder
    -0.60
    Kilder
    -0.59
    KommentareTeilen
    -0.58
    :-)
    -0.58
    ChromeDriver
    -0.58
     contd
    -0.57
    OREM
    -0.57
     Etc
    -0.57
    POSITIVE LOGITS
     
    0.65
    . 
    0.58
     Ubicación
    0.53
    RegistryLite
    0.52
    Whilst
    0.52
    recogn
    0.51
    ‍
    0.51
    ’.
    0.51
    ’
    0.50
    Commenting
    0.49
    Activations Density 0.143%

    No Known Activations