© 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. 34-GEMMASCOPE-RES-16K
    11. 11613
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to communication or interaction involving named individuals, particularly with the suffix 'ing'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.47
    #+#
    -0.47
     proszę
    -0.40
    Cuál
    -0.40
    bial
    -0.39
    OOTD
    -0.39
    protoimpl
    -0.39
     fört
    -0.38
    devamını
    -0.37
     fören
    -0.37
    POSITIVE LOGITS
    etje
    0.57
    gggg
    0.55
    ging
    0.55
    ค์
    0.53
    ggg
    0.53
    ering
    0.52
     Ing
    0.50
     Zing
    0.50
     pong
    0.49
    ding
    0.48
    Activations Density 0.221%

    No Known Activations