© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    key terms related to signs of intoxication, requirements in various contexts, and other critical conditions or observations

    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
    +0.26
    1.0%
    1870
    +0.10
    0.4%
    184
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.26
    0.07
    1870
    +0.10
    0.05
    332
    +0.07
    0.06
    Negative Logits
    <bos>
    -2.73
    ⓧ
    -1.11
    
    -1.01
    <?
    -0.85
    /**
    -0.84
    /*
    -0.76
    /***
    -0.76
    Примеча
    -0.68
    //---
    -0.66
    //{
    -0.64
    POSITIVE LOGITS
     tungkol
    0.76
     paradiso
    0.73
     pymysql
    0.70
    intelligible
    0.68
    dirond
    0.66
     tramonto
    0.66
     galore
    0.66
    favourable
    0.65
    nemia
    0.65
     sarili
    0.63
    Activations Density 0.619%

    No Known Activations