© 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. 1891
    Prev
    Next
    INDEX
    Explanations

    topics related to freedom and civic rights

    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
    +0.28
    1.1%
    1842
    +0.15
    0.6%
    1741
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.28
    0.13
    1870
    +0.15
    0.09
    1842
    +0.13
    0.07
    Negative Logits
    <bos>
    -2.24
     republi
    -0.83
     solidar
    -0.83
     cooperated
    -0.74
    /***
    -0.71
     rek
    -0.71
    },{
    -0.71
    ⓧ
    -0.70
    }],
    -0.70
     dras
    -0.68
    POSITIVE LOGITS
     bandung
    1.26
     ecru
    1.20
     cavallo
    1.19
     paradiso
    1.19
     clô
    1.18
     réjou
    1.16
     cæ
    1.13
     écout
    1.12
     unwarran
    1.11
     carrefour
    1.08
    Activations Density 1.267%

    No Known Activations