© 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 EvalsExportsinterp-engineNEWAPI 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. 5126
    Prev
    Next
    INDEX
    Explanations

    economic data, including personal income growth statistics and average per capita income figures

    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
    1253
    +0.15
    0.5%
    1445
    +0.12
    0.4%
    1385
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.15
    0.05
    1241
    +0.12
    0.04
    739
    +0.10
    0.02
    Negative Logits
     encomp
    -1.57
     resear
    -1.53
     volunte
    -1.51
     intersper
    -1.51
     maneu
    -1.50
     accla
    -1.49
     inev
    -1.45
     emphat
    -1.45
     depic
    -1.41
     shenan
    -1.39
    POSITIVE LOGITS
     average
    0.76
    average
    0.73
    Average
    0.72
     Average
    0.67
    median
    0.66
    <bos>
    0.65
     median
    0.64
    Median
    0.58
     mediana
    0.57
    income
    0.56
    Activations Density 0.233%

    No Known Activations