© 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. 8258
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progression or moving forward in time

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

    "which brings us/me to"

    np_acts-logits-general · gemini-2.0-flash

    brings us to

    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
     kasarigan
    -1.07
     transfieras
    -0.88
    ftagPool
    -0.87
     nakalista
    -0.86
    yarnpkg
    -0.77
    ViewFeatures
    -0.75
    principalColumn
    -0.75
     '\\;'
    -0.72
    esgue
    -0.71
     initComponents
    -0.70
    POSITIVE LOGITS
    Fast
    1.35
     Fast
    1.29
     fast
    1.26
    fast
    1.16
     skip
    1.05
    Skip
    0.91
    skip
    0.88
     Skip
    0.86
     FAST
    0.86
    FAST
    0.83
    Activations Density 0.209%

    No Known Activations