© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13360
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports, particularly football and baseball

    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
    382
    +0.10
    0.3%
    974
    +0.09
    0.2%
    674
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    974
    +0.10
    0.04
    2032
    +0.09
    0.04
    534
    +0.08
    0.04
    Negative Logits
     kram
    -0.85
     traktor
    -0.81
     lemp
    -0.80
     teras
    -0.79
     labd
    -0.79
     augus
    -0.78
     kac
    -0.77
     tomat
    -0.76
     lele
    -0.76
     alkoh
    -0.76
    POSITIVE LOGITS
     reluct
    0.78
     indeed
    0.75
     disreg
    0.75
     philanth
    0.73
     fortunately
    0.72
     shenan
    0.69
     thankfully
    0.69
    indeed
    0.68
     unve
    0.67
     luckily
    0.66
    Activations Density 0.458%

    No Known Activations