© 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. 507
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific or technical processes and measurements

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

    Text followed by a question mark

    np_acts-logits-general · gemini-2.0-flash

    measurements and scientific terms

    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
     Normdatei
    -0.89
    TagMode
    -0.86
    JspWriter
    -0.84
    parsedMessage
    -0.83
     CreateTagHelper
    -0.83
    ftagPool
    -0.80
     defaultstate
    -0.78
    UnusedPrivate
    -0.77
    PerformLayout
    -0.77
    EndInit
    -0.76
    POSITIVE LOGITS
    ’
    0.72
     design
    0.66
    '
    0.65
     progress
    0.62
    의
    0.61
    ின்
    0.57
     final
    0.57
     itself
    0.57
     initial
    0.56
     dis
    0.54
    Activations Density 1.856%

    No Known Activations