© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    references to significant or shocking events and their explanations

    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
    +0.27
    0.9%
    872
    +0.09
    0.3%
    1978
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1054
    +0.27
    0.04
    70
    +0.09
    0.05
    1905
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.45
    /***
    -0.98
     intersper
    -0.88
    <^
    -0.86
    :,,
    -0.83
    Derp
    -0.81
     »>
    -0.78
    //*/
    -0.77
     endow
    -0.76
    //---
    -0.74
    POSITIVE LOGITS
     marea
    0.80
    ungalow
    0.79
     palio
    0.78
     paradiso
    0.78
     cioc
    0.73
     riva
    0.71
     soggior
    0.70
    straint
    0.70
     vacanza
    0.70
     mezza
    0.70
    Activations Density 0.935%

    No Known Activations