© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 2710
    Prev
    Next
    INDEX
    Explanations

    key terms related to blockchain transactions and security mechanisms

    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
    +0.25
    1.0%
    946
    +0.12
    0.5%
    876
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.25
    0.05
    1553
    +0.12
    0.06
    1252
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.33
    echo
    -0.66
    public
    -0.60
    displayquote
    -0.59
    https
    -0.59
    RequestMapping
    -0.59
    /***
    
    -0.58
    Globalization
    -0.58
    http
    -0.57
    Descripció
    -0.57
    POSITIVE LOGITS
     swarovski
    1.81
     michelin
    1.75
     lamborghini
    1.75
     eiffel
    1.74
     wien
    1.72
     stockholm
    1.72
     chrysler
    1.72
     riviera
    1.66
     hilux
    1.66
     peugeot
    1.64
    Activations Density 0.890%

    No Known Activations