© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11306
    Prev
    Next
    INDEX
    Explanations

    details about a poor farming family and educational challenges faced by a person in the family

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    Descriptions of economic hardship and basic survival (poverty, lack of resources, work to make ends meet, lost education, forced labor/marriage, and related struggle).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    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
    184
    +0.17
    0.5%
    1703
    +0.13
    0.4%
    1120
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.17
    0.02
    610
    +0.13
    0.04
    944
    +0.11
    0.02
    Negative Logits
     Minang
    -1.18
     bandung
    -1.18
     kug
    -1.18
     laci
    -1.17
     Seni
    -1.17
     kram
    -1.15
     lapto
    -1.14
     gila
    -1.13
     Jasa
    -1.12
     lele
    -1.12
    POSITIVE LOGITS
     village
    0.58
     referrerpolicy
    0.55
     getItemId
    0.54
    ciless
    0.53
    smöglichkeiten
    0.52
     lány
    0.51
    ğından
    0.51
     Ebenso
    0.51
     őket
    0.50
    SequentialGroup
    0.50
    Activations Density 0.445%

    No Known Activations