© 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. 35-GEMMASCOPE-RES-16K
    11. 12305
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal connections and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.72
    IUrlHelper
    -0.44
     jeg
    -0.43
    SourceChecksum
    -0.40
    TabIndex
    -0.39
     sein
    -0.35
    I
    -0.35
    MemoryWarning
    -0.34
     we
    -0.33
    weakSelf
    -0.31
    POSITIVE LOGITS
     my
    2.88
    我的
    1.84
     mijn
    1.78
    my
    1.73
     meinen
    1.61
     meu
    1.61
     meinem
    1.61
     minha
    1.58
     meus
    1.52
     miei
    1.52
    Activations Density 1.108%

    No Known Activations