© 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. 13220
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal investigations and bureaucratic processes

    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
    1741
    +0.15
    0.5%
    1967
    +0.13
    0.4%
    674
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1187
    +0.15
    0.03
    492
    +0.13
    0.04
    1763
    +0.11
    0.03
    Negative Logits
     smtplib
    -0.75
     PLWABN
    -0.70
     pymysql
    -0.70
    Sklici
    -0.69
     psycopg
    -0.62
     heapq
    -0.62
     Shakspeare
    -0.62
     begrij
    -0.61
     vergeten
    -0.59
     bevestig
    -0.58
    POSITIVE LOGITS
     monaster
    0.79
     ideolog
    0.76
     OVER
    0.74
     over
    0.73
     Over
    0.70
     utop
    0.69
    Over
    0.65
     republi
    0.64
    <bos>
    0.63
     conflic
    0.61
    Activations Density 0.073%

    No Known Activations