© 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. 12473
    Prev
    Next
    INDEX
    Explanations

    phrases related to suggestions and considerations in decision-making contexts

    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
     becoming
    -0.48
    되어
    -0.48
    becoming
    -0.47
     disfrutando
    -0.46
     convertirse
    -0.46
     devenir
    -0.45
     cumplir
    -0.44
     interacting
    -0.44
     comprends
    -0.43
     disfr
    -0.43
    POSITIVE LOGITS
    让
    0.90
     introduce
    0.84
    讓
    0.81
    Introduce
    0.81
     Introduce
    0.80
    把
    0.79
     placing
    0.77
     letting
    0.75
     assign
    0.75
     allow
    0.74
    Activations Density 1.496%

    No Known Activations