© 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. 4502
    Prev
    Next
    INDEX
    Explanations

    phrases expressing large quantities or comparisons

    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
    1525
    +0.09
    0.2%
    152
    +0.08
    0.2%
    468
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1368
    +0.09
    0.03
    1525
    +0.08
    0.04
    683
    +0.08
    0.04
    Negative Logits
     wherea
    -1.04
     indestru
    -0.97
     excru
    -0.92
     encomp
    -0.91
     shenan
    -0.90
     impractica
    -0.88
     affor
    -0.88
     Souha
    -0.85
     impra
    -0.84
     accla
    -0.83
    POSITIVE LOGITS
     evidence
    0.62
    tonsoft
    0.60
     ویکی‌پدیای
    0.58
     كومونز
    0.55
    interesse
    0.52
    tillerie
    0.52
    evidence
    0.51
     tonel
    0.51
     information
    0.50
    原始内容
    0.50
    Activations Density 0.190%

    No Known Activations