© 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. 28-GEMMASCOPE-RES-16K
    6. 4806
    Prev
    Next
    INDEX
    Explanations

    relationships between gender, age, and various health traits or conditions

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

    gender

    np_acts-logits-general · gemini-2.0-flash

    male and female terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.51
    AddTagHelper
    -0.48
    #
    -0.46
    VYMaps
    -0.45
    LookAnd
    -0.45
    badah
    -0.44
    Geplaatst
    -0.44
    omitempty
    -0.44
     utafitiHapana
    -0.43
     RVA
    -0.42
    POSITIVE LOGITS
     female
    2.16
     male
    2.08
     females
    1.98
    female
    1.91
     Female
    1.87
     women
    1.84
     males
    1.83
     gender
    1.82
    Female
    1.80
    male
    1.76
    Activations Density 0.839%

    No Known Activations