© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7820
    Prev
    Next
    INDEX
    Explanations

    terms related to transportation, particularly focusing on railways and passenger services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    dagangan
    -0.38
    griffe
    -0.36
    empuan
    -0.36
     getir
    -0.36
     đánh
    -0.36
     Infór
    -0.36
    encodeWith
    -0.36
    abinieri
    -0.36
    almost
    -0.35
     cuidadosamente
    -0.35
    POSITIVE LOGITS
    AndEndTag
    0.53
     purposes
    0.52
     purpoſe
    0.51
    ductory
    0.49
     pleaſure
    0.47
    MockMvc
    0.46
    SwitchCompat
    0.45
    Bioaccumulative
    0.44
    TagMode
    0.44
     незавершена
    0.43
    Activations Density 0.555%

    No Known Activations