© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3647
    Prev
    Next
    INDEX
    Explanations

    references to conflicts and rules within a specified context

    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
    1842
    +0.36
    1.5%
    1967
    +0.29
    1.2%
    1577
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.36
    0.10
    1385
    +0.29
    0.11
    498
    +0.17
    0.07
    Negative Logits
    <bos>
    -2.89
    
    -1.13
    ⓧ
    -1.01
    /**
    -0.89
     censiti
    -0.88
    bardziej
    -0.86
    ształ
    -0.84
    <?
    -0.84
    lepiej
    -0.80
     يتيمه
    -0.79
    POSITIVE LOGITS
     pira
    0.89
     parati
    0.84
     sord
    0.84
     ↔
    0.80
     □
    0.77
     fono
    0.77
     intest
    0.76
     démoc
    0.75
     bamb
    0.74
     gesta
    0.74
    Activations Density 1.267%

    No Known Activations