© 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. 14682
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or ranking

    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
    1491
    +0.12
    0.4%
    1381
    +0.12
    0.4%
    421
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1491
    +0.12
    0.03
    1381
    +0.12
    0.03
    78
    +0.11
    0.02
    Negative Logits
     pompa
    -0.54
     interag
    -0.54
     interrom
    -0.54
     furg
    -0.52
     kask
    -0.51
     rapor
    -0.51
     panik
    -0.50
    úde
    -0.50
     komik
    -0.50
     sedia
    -0.50
    POSITIVE LOGITS
     Placing
    1.13
     placed
    1.10
     placement
    1.07
     placing
    1.06
    placed
    1.05
     placements
    1.04
     Placement
    0.96
     Placed
    0.94
     PLACE
    0.93
     Place
    0.93
    Activations Density 0.079%

    No Known Activations