© 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. 3604
    Prev
    Next
    INDEX
    Explanations

    statements that dispute or challenge the validity of claims

    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
    0.9%
    1150
    +0.12
    0.4%
    872
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.27
    0.09
    1791
    +0.12
    0.07
    12
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.14
    /***
    -0.81
    ///**
    -0.76
    
    -0.66
    /*!
    -0.64
    Autoritní
    -0.64
    ⓧ
    -0.61
    bewerken
    -0.60
    <!--
    -0.59
    RegressionTest
    -0.57
    POSITIVE LOGITS
     thuy
    0.83
     Muhamma
    0.77
     soste
    0.76
     Khart
    0.74
     mezza
    0.74
     heapq
    0.73
     paradiso
    0.68
     maroc
    0.68
     untrue
    0.67
     inaccurate
    0.66
    Activations Density 0.772%

    No Known Activations