© 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. 11878
    Prev
    Next
    INDEX
    Explanations

    numerical measurements and comparisons

    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
    1265
    +0.13
    0.5%
    411
    +0.13
    0.5%
    976
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    976
    +0.13
    0.05
    1356
    +0.13
    0.04
    411
    +0.12
    0.04
    Negative Logits
     layui
    -0.53
     kasa
    -0.49
     kac
    -0.49
     farbe
    -0.48
     zara
    -0.46
     bera
    -0.46
     kosme
    -0.46
     kamb
    -0.45
     kön
    -0.45
     kand
    -0.45
    POSITIVE LOGITS
    much
    0.89
    Much
    0.84
     MUCH
    0.82
     much
    0.82
     Much
    0.77
    <bos>
    0.65
    otheby
    0.62
     tricot
    0.59
     murano
    0.58
    postolic
    0.57
    Activations Density 0.081%

    No Known Activations