© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11023
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations, particularly ports

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

    the word "Port" followed by proper nouns (place names or geographic locations).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.58
    الدراسه
    -0.53
    mybatisplus
    -0.51
    tagext
    -0.44
    labus
    -0.44
    makeText
    -0.43
    paravant
    -0.41
    новништво
    -0.40
     Huxley
    -0.39
     Regelung
    -0.39
    POSITIVE LOGITS
     Port
    0.69
     PORT
    0.68
     Пор
    0.65
     POR
    0.63
     Por
    0.61
    NameInMap
    0.58
    getPort
    0.56
    Port
    0.55
     port
    0.54
     por
    0.53
    Activations Density 0.126%

    No Known Activations