© 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. 20-GEMMASCOPE-RES-16K
    11. 14872
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to engineering and electrical components

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

    Followed by "said" or similar word

    np_acts-logits-general · gemini-2.0-flash

    said, exposing, crossing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.59
    Rhestr
    -0.56
     تضيفلها
    -0.53
    IUrlHelper
    -0.52
    Portail
    -0.52
     SwitchCompat
    -0.51
    ivasan
    -0.50
    onAttach
    -0.50
    рные
    -0.50
     هنا
    -0.50
    POSITIVE LOGITS
     said
    3.43
    said
    2.63
    Said
    2.49
     Said
    2.37
     SAID
    2.25
     ladite
    1.85
     dicho
    1.84
     faid
    1.80
     dicha
    1.69
     aforesaid
    1.67
    Activations Density 1.059%

    No Known Activations