© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    negations or contrasting statements in discussions about societal norms and behaviors

    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
    +0.22
    1.1%
    298
    +0.09
    0.5%
    478
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.22
    0.02
    1472
    +0.09
    0.02
    849
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.58
    
    -0.78
    CodeDom
    -0.76
    lateinit
    -0.76
    ⓧ
    -0.75
    }());
    -0.69
    //</
    -0.65
    GeneratedCode
    -0.65
    /**
    -0.63
    get
    -0.63
    POSITIVE LOGITS
     unlaw
    1.61
     maneu
    1.48
     pamph
    1.47
     affor
    1.45
     swarovski
    1.41
     balenciaga
    1.40
     disagre
    1.40
     increa
    1.40
     gabri
    1.39
     ecru
    1.39
    Activations Density 0.034%

    No Known Activations