© 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. 35-GEMMASCOPE-RES-16K
    6. 6474
    Prev
    Next
    INDEX
    Explanations

    references to different demographic groups, particularly focusing on age and gender

    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
    ADATA
    -0.46
    FirstResponder
    -0.41
     Bioaccumulative
    -0.36
    hubaneswar
    -0.35
    vois
    -0.33
    GeneratedValue
    -0.32
     playbook
    -0.32
    Politique
    -0.32
    urlencoded
    -0.32
     defaultstate
    -0.32
    POSITIVE LOGITS
     age
    3.66
     ages
    3.03
     Age
    3.00
    Age
    2.80
     aged
    2.70
     edad
    2.64
     AGE
    2.59
     âge
    2.53
     Ages
    2.42
    age
    2.39
    Activations Density 0.858%

    No Known Activations