© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 316
    Prev
    Next
    INDEX
    Explanations

    numerical data and scores related to various assessments, possibly in a psychological 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
    50
    +0.27
    1.1%
    1343
    +0.14
    0.6%
    184
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.27
    0.06
    1699
    +0.14
    0.04
    1596
    +0.08
    0.04
    Negative Logits
    <bos>
    -3.52
    ⓧ
    -1.19
    
    
    -1.04
    /**
    -1.03
    contentLoaded
    -0.91
     disbur
    -0.90
    <?
    -0.90
    /***
    
    -0.88
     intersper
    -0.84
    /*
    -0.82
    POSITIVE LOGITS
     Outils
    0.77
     Longueur
    0.76
     manuten
    0.74
     Hauteur
    0.73
     Kategor
    0.73
     erit
    0.72
     marea
    0.72
     santiago
    0.72
     cæ
    0.71
     ché
    0.71
    Activations Density 0.142%

    No Known Activations