© 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. 4149
    Prev
    Next
    INDEX
    Explanations

    sections that discuss summaries, analyses, or evaluations of concepts and their applications

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

    Expressing manner, method, or explanation

    np_acts-logits-general · gemini-2.0-flash

    explaining how and ways

    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
    DOCTYPE
    -0.60
    twimg
    -0.58
     BorderRadius
    -0.57
    Datuak
    -0.57
    ReusableCell
    -0.55
     विश्वसनीयता
    -0.53
     TextInputType
    -0.52
    SequentialGroup
    -0.52
    nagel
    -0.52
    VYMaps
    -0.52
    POSITIVE LOGITS
     how
    2.37
    how
    1.83
     ways
    1.64
    How
    1.59
     How
    1.56
     cómo
    1.41
     bagaimana
    1.34
    HOW
    1.32
     چگونه
    1.30
     hvordan
    1.29
    Activations Density 0.356%

    No Known Activations