© 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. 9849
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to brevity or short duration

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

    "short"

    np_acts-logits-general · gemini-2.0-flash

    short-term

    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
    DidLoad
    -0.71
    /*
    -0.69
    StoryboardSegue
    -0.67
     ""],
    -0.67
    iteracy
    -0.67
     AssemblyVersion
    -0.66
    FormTagHelper
    -0.64
    (',',
    -0.64
     שוליים
    -0.63
    =""/>
    -0.63
    POSITIVE LOGITS
     Short
    1.31
     short
    1.29
    Short
    1.28
     SHORT
    1.28
    SHORT
    1.24
    short
    1.18
     Shorts
    1.06
     shorts
    0.98
     shor
    0.95
    Shorts
    0.92
    Activations Density 0.119%

    No Known Activations