© 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. 3832
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving multiplication

    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
    438
    +0.08
    0.2%
    1053
    +0.08
    0.2%
    1407
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.08
    0.03
    870
    +0.08
    0.03
    1407
    +0.08
    0.02
    Negative Logits
     hej
    -0.65
     kade
    -0.64
    ----</
    -0.64
     teras
    -0.62
     palab
    -0.61
    Carreira
    -0.61
     elek
    -0.59
    бият
    -0.59
     kaos
    -0.59
     meras
    -0.56
    POSITIVE LOGITS
     cushi
    1.00
     Whence
    0.99
     disagre
    0.95
     McLaugh
    0.93
     unspeak
    0.91
     vainly
    0.88
     unwarran
    0.87
     apprehen
    0.87
     reluct
    0.85
     depic
    0.84
    Activations Density 0.072%

    No Known Activations