© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 258
    Prev
    Next
    INDEX
    Explanations

    actions and choices related to consumer behavior and decision-making

    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
    +0.26
    1.1%
    184
    +0.17
    0.7%
    394
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.26
    0.03
    876
    +0.17
    -0.04
    394
    +0.17
    0.07
    Negative Logits
    <bos>
    -3.07
    .
    -0.82
    。
    -0.67
    displayquote
    -0.67
    contentLoaded
    -0.67
     also
    -0.66
    <eos>
    -0.66
    ↵↵
    -0.65
    endif
    -0.64
    public
    -0.62
    POSITIVE LOGITS
     stockholm
    1.71
     wien
    1.70
     swarovski
    1.70
     bordeaux
    1.61
     magis
    1.61
     ecru
    1.59
     frankfurt
    1.58
     eiffel
    1.56
     desir
    1.55
     🤣🤣
    1.55
    Activations Density 1.278%

    No Known Activations