© 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. 1924
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, especially focusing on specific places like Jordan or Jericho

    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
    1909
    +0.21
    1.0%
    1222
    +0.20
    0.9%
    1892
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1909
    +0.21
    0.03
    1222
    +0.20
    0.02
    1376
    +0.16
    0.02
    Negative Logits
    ibatis
    -0.56
     onFailure
    -0.48
     кӀош
    -0.47
     käns
    -0.47
    Hä
    -0.46
    Петербург
    -0.46
    República
    -0.46
     يتيمه
    -0.45
     nakalista
    -0.45
    PushButton
    -0.44
    POSITIVE LOGITS
     jordan
    1.56
     Jordan
    1.51
     JORDAN
    1.48
    Jordan
    1.41
     Jord
    1.24
     emphat
    1.18
    jordan
    1.18
     fuf
    1.10
     Jordanian
    1.08
     accla
    1.07
    Activations Density 0.117%

    No Known Activations