© 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. 14747
    Prev
    Next
    INDEX
    Explanations

    NFL player names related to the Lions team and their contracts

    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
    630
    +0.12
    0.4%
    612
    +0.12
    0.4%
    1843
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.12
    0.01
    981
    +0.12
    0.05
    1343
    +0.11
    0.05
    Negative Logits
    LookAnd
    -0.68
    nmgp
    -0.46
    AsUp
    -0.45
     enrique
    -0.43
    хьтан
    -0.43
     fieldNum
    -0.43
    <bos>
    -0.41
    towania
    -0.41
     Municip
    -0.39
    waitKey
    -0.39
    POSITIVE LOGITS
     vhs
    0.63
     psycopg
    0.60
     pymysql
    0.59
     heapq
    0.59
     Endlich
    0.57
     cabrio
    0.54
     afk
    0.53
    ytick
    0.53
     jojo
    0.52
     uninten
    0.52
    Activations Density 0.382%

    No Known Activations