© 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. 12667
    Prev
    Next
    INDEX
    Explanations

    quite a variety of things related to personal descriptions and community discussions

    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
    1385
    +0.12
    0.4%
    1967
    +0.11
    0.4%
    674
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    942
    +0.12
    0.04
    1505
    +0.11
    0.03
    249
    +0.11
    0.04
    Negative Logits
    !=-
    -0.62
     habang
    -0.58
     kapag
    -0.57
     mwenye
    -0.57
     tayo
    -0.57
    ==="
    -0.57
     iliy
    -0.55
     wako
    -0.55
     strerror
    -0.54
     kutoka
    -0.53
    POSITIVE LOGITS
     reputa
    0.70
     airpods
    0.64
     same
    0.64
     sappi
    0.62
     tricot
    0.61
     tupperware
    0.61
     teflon
    0.61
     venuto
    0.60
     utop
    0.59
     xperia
    0.59
    Activations Density 0.138%

    No Known Activations