© 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. 7309
    Prev
    Next
    INDEX
    Explanations

    key events or agreements in business or political contexts

    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
    991
    +0.12
    0.3%
    1085
    +0.09
    0.2%
    1413
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    991
    +0.12
    0.04
    347
    +0.09
    0.03
    1413
    +0.08
    0.03
    Negative Logits
     Illus
    -0.96
     encomp
    -0.94
     reluct
    -0.86
     Daven
    -0.84
     depic
    -0.83
     indestru
    -0.82
     impra
    -0.82
     unspeak
    -0.82
     Middles
    -0.81
     Confu
    -0.80
    POSITIVE LOGITS
     reach
    0.78
    reach
    0.69
     reaches
    0.67
     reached
    0.65
    reached
    0.64
     reaching
    0.60
     reputa
    0.60
    reaching
    0.59
     milestone
    0.58
     threshold
    0.57
    Activations Density 0.226%

    No Known Activations