© 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. 11381
    Prev
    Next
    INDEX
    Explanations

    references to statistics, evaluations, or inquiries related to various subjects

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

    that describe the composition or properties of something

    np_acts-logits-general · gemini-2.0-flash

    contains or lacks components

    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
     valamint
    -0.60
     wtedy
    -0.53
    GroupLayout
    -0.53
     kuin
    -0.51
    SessionFactory
    -0.51
     niż
    -0.50
    才能
    -0.50
    AxisAlignment
    -0.49
    than
    -0.47
     hanem
    -0.47
    POSITIVE LOGITS
     contains
    0.89
     contain
    0.81
     resembles
    0.76
     consists
    0.72
     lacks
    0.72
     ressemble
    0.71
     possède
    0.71
     memiliki
    0.70
     includes
    0.69
     doesn
    0.69
    Activations Density 0.879%

    No Known Activations