© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6995
    Prev
    Next
    INDEX
    Explanations

    instances of personal references and self-identification

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

    Words/phrases followed by "aside"

    np_acts-logits-general · gemini-2.0-flash

    separating or setting aside discussion

    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
    Tikang
    -0.88
     >=",
    -0.81
    AndEndTag
    -0.61
    AutoresizingMask
    -0.60
     nakalista
    -0.59
     виправивши
    -0.57
    AccessorTable
    -0.57
    wieś
    -0.56
    IContainer
    -0.55
    featureID
    -0.55
    POSITIVE LOGITS
     aside
    2.37
     notwithstanding
    2.16
    aside
    1.61
     Aside
    1.53
     apart
    1.52
     excepted
    1.46
    Aside
    1.38
    apart
    1.23
    withstanding
    1.23
     aparte
    1.23
    Activations Density 0.267%

    No Known Activations