© 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. 7-GEMMASCOPE-RES-16K
    6. 11405
    Prev
    Next
    INDEX
    Explanations

    elements related to progress indicators and error/warning messages in web design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.85
    Personendaten
    -0.76
    EndInit
    -0.74
    GEBURTSDATUM
    -0.69
     createSprite
    -0.69
     auffi
    -0.68
    TagMode
    -0.67
    JspWriter
    -0.62
    richTextPanel
    -0.61
     Signalez
    -0.61
    POSITIVE LOGITS
     client
    0.50
    Syna
    0.50
     SYN
    0.49
    ')}}"
    0.48
    ()}}
    0.48
    fclose
    0.48
    schod
    0.47
    MemoryWarning
    0.46
    aults
    0.46
    ztus
    0.46
    Activations Density 0.206%

    No Known Activations