© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 529
    Prev
    Next
    INDEX
    Explanations

    references to pistols and handguns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    506
    +0.20
    1.1%
    410
    +0.15
    0.8%
    31
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1575
    +0.20
    0.03
    227
    +0.15
    0.04
    1741
    +0.15
    0.00
    Negative Logits
    <bos>
    -0.97
    Lees
    -0.62
    pgfplots
    -0.58
    ftagPool
    -0.55
    Grüße
    -0.55
    Chiara
    -0.54
    redhat
    -0.53
    Život
    -0.52
    Dunk
    -0.51
    dout
    -0.51
    POSITIVE LOGITS
     Pistol
    0.90
     pistol
    0.87
     pistols
    0.76
     bosco
    0.76
     cincin
    0.76
     vne
    0.75
     hej
    0.74
    pist
    0.73
     siff
    0.73
     golfe
    0.73
    Activations Density 0.214%

    No Known Activations