Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6830
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice and discrimination issues, particularly focusing on laws and policies affecting marginalized communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.53
    stdc
    -0.50
    Eccles
    -0.45
    gameserver
    -0.45
     lados
    -0.45
    usehen
    -0.45
     something
    -0.44
    VBox
    -0.44
     kepolisian
    -0.44
    requestCode
    -0.44
    POSITIVE LOGITS
     people
    0.90
     young
    0.86
     individuals
    0.78
     persons
    0.74
     snippetHide
    0.74
     senior
    0.71
     everyone
    0.69
     anyone
    0.69
    young
    0.67
    ผู้
    0.67
    Activations Density 1.149%

    No Known Activations