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

    Neuronpedia

    Jacobian LensNEW
    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. 15293
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with tranquility and silence

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

    "quiet" or similar concepts (silent, silence)

    np_acts-logits-general · gemini-2.0-flash

    quiet or silence

    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
    AndEndTag
    -0.76
    rinfo
    -0.65
    出版年
    -0.64
    +:+
    -0.62
    sidemargin
    -0.61
    AddWithValue
    -0.61
    thme
    -0.61
    RegistryLite
    -0.61
    OGND
    -0.59
     CreateTagHelper
    -0.59
    POSITIVE LOGITS
     Quiet
    1.21
    Quiet
    1.12
     quiet
    1.08
     silent
    1.05
     Silent
    1.03
    Silent
    0.96
     quieter
    0.94
    quiet
    0.93
     silence
    0.92
     Silence
    0.88
    Activations Density 0.159%

    No Known Activations