© 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. 6422
    Prev
    Next
    INDEX
    Explanations

    sentences related to economics and social 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
    2034
    +0.16
    0.5%
    2019
    +0.13
    0.4%
    1510
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.16
    0.07
    382
    +0.13
    0.07
    1381
    +0.10
    0.06
    Negative Logits
     mef
    -1.70
     istan
    -1.65
     fta
    -1.65
     aen
    -1.64
     lele
    -1.59
     jaya
    -1.58
     fte
    -1.57
     sii
    -1.56
     umo
    -1.55
     hina
    -1.53
    POSITIVE LOGITS
     but
    0.91
     although
    0.89
     especially
    0.87
     however
    0.86
     regardless
    0.85
     which
    0.82
     including
    0.81
     whether
    0.81
     albeit
    0.81
     though
    0.81
    Activations Density 0.417%

    No Known Activations