© 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. 2014
    Prev
    Next
    INDEX
    Explanations

    words related to education, architecture, and gender issues

    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
    674
    +0.12
    0.3%
    872
    +0.09
    0.2%
    1042
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1358
    +0.12
    0.04
    967
    +0.09
    0.03
    676
    +0.07
    0.04
    Negative Logits
     pixabay
    -1.18
     gettyimages
    -1.15
     meis
    -1.15
     lara
    -1.12
     shutterstock
    -1.11
     dises
    -1.08
     wien
    -1.08
     haup
    -1.08
     fta
    -1.07
     ciga
    -1.07
    POSITIVE LOGITS
    <bos>
    1.04
     but
    0.70
     sondern
    0.69
     nor
    0.69
    but
    0.64
     But
    0.61
    writeFieldEnd
    0.60
     nhưng
    0.59
     pero
    0.57
     merely
    0.56
    Activations Density 0.236%

    No Known Activations