© 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. 2466
    Prev
    Next
    INDEX
    Explanations

    words related to the emergence or occurrence of events or conditions

    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
    50
    +0.18
    0.8%
    156
    +0.12
    0.5%
    1937
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1512
    +0.18
    0.03
    537
    +0.12
    0.03
    284
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.43
     keep
    -0.63
     kill
    -0.60
     durar
    -0.59
    frac
    -0.58
    Fal
    -0.57
    public
    -0.57
     average
    -0.57
    cout
    -0.57
     commercial
    -0.56
    POSITIVE LOGITS
     tupperware
    1.46
     madonna
    1.35
     fortn
    1.26
     maneu
    1.24
     panama
    1.23
     ecru
    1.22
     stockholm
    1.21
     milf
    1.21
     outlander
    1.20
     burberry
    1.19
    Activations Density 0.116%

    No Known Activations