© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2044
    Prev
    Next
    INDEX
    Explanations

    mentions of African-related terms or identities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    871
    +0.15
    0.6%
    1334
    +0.13
    0.5%
    1065
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.15
    0.04
    1407
    +0.13
    0.03
    1065
    +0.13
    0.03
    Negative Logits
    قایناق‌لار
    -0.54
    setDo
    -0.51
    IsInitialized
    -0.50
    fnamefont
    -0.49
    zepam
    -0.49
     חיצוניים
    -0.47
    tils
    -0.47
    Diweddarwch
    -0.46
    vek
    -0.46
    AddTagHelper
    -0.45
    POSITIVE LOGITS
     African
    1.23
     afric
    1.23
    African
    1.15
     african
    1.14
     Africa
    1.13
     Lmao
    1.12
     hentai
    1.11
     Wtf
    1.10
     AFRICAN
    1.07
     Africans
    1.06
    Activations Density 0.071%

    No Known Activations