© 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. 11495
    Prev
    Next
    INDEX
    Explanations

    information related to the historical or current usage of buildings

    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
    1805
    +0.13
    0.5%
    1034
    +0.11
    0.4%
    1339
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.13
    0.03
    1059
    +0.11
    0.03
    1437
    +0.11
    0.03
    Negative Logits
     nicolas
    -0.88
     yves
    -0.84
     scrat
    -0.83
     encomp
    -0.82
     alberto
    -0.81
     gabri
    -0.80
     affor
    -0.79
     intersper
    -0.78
     claudia
    -0.77
     sergio
    -0.75
    POSITIVE LOGITS
     building
    1.30
    building
    1.25
     buildings
    1.21
     Building
    1.21
    Building
    1.14
     Buildings
    1.13
     BUILDING
    1.07
    buildings
    1.03
    BUILDING
    0.99
    Buildings
    0.93
    Activations Density 0.074%

    No Known Activations