© 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. 10733
    Prev
    Next
    INDEX
    Explanations

    segments of text where there are no significant activations indicating specific content

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

    Code snippets and non-English words

    np_acts-logits-general · gemini-2.0-flash

    synthetic THC

    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
    Personendaten
    -0.74
    RegressionTest
    -0.67
    Personensuche
    -0.60
     otomatig
    -0.57
     Administrativna
    -0.56
    Alike
    -0.53
     defaultstate
    -0.53
    onomy
    -0.52
     OFDb
    -0.51
    transQ
    -0.50
    POSITIVE LOGITS
     متعلقه
    0.62
    SequentialGroup
    0.58
    feinander
    0.55
    SpringBootTest
    0.54
    ніципалі
    0.51
    FIGURE
    0.50
     lenker
    0.50
    WHM
    0.49
    épend
    0.49
     pendiente
    0.48
    Activations Density 0.076%

    No Known Activations