© 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. 2484
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal choices and women's autonomy over their bodies

    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
    +0.32
    1.1%
    1967
    +0.07
    0.3%
    460
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    644
    +0.32
    0.04
    17
    +0.07
    0.03
    819
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.48
    
    -0.82
    /***
    -0.82
    /*!
    -0.79
     ratify
    -0.78
    ⓧ
    -0.75
     intersper
    -0.74
     endeavored
    -0.71
     incarcer
    -0.71
     endeavoured
    -0.70
    POSITIVE LOGITS
     croce
    0.86
     marea
    0.81
     expériment
    0.78
     pleins
    0.77
     riva
    0.77
     montagna
    0.76
     maroc
    0.75
     sfera
    0.75
     ferie
    0.75
     signora
    0.74
    Activations Density 0.499%

    No Known Activations