© 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. 248
    Prev
    Next
    INDEX
    Explanations

    names of species and their classifications

    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
    +0.17
    0.7%
    227
    +0.17
    0.7%
    1741
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.04
    113
    +0.17
    0.02
    283
    +0.17
    0.01
    Negative Logits
    <bos>
    -2.71
    ⓧ
    -1.29
    /**
    -0.90
    
    -0.90
    <?
    -0.90
    /*
    -0.82
    otheby
    -0.80
    énégal
    -0.73
     censiti
    -0.70
    Personensuche
    -0.70
    POSITIVE LOGITS
     reft
    1.22
     affor
    1.21
     increa
    1.20
     unden
    1.19
     ftu
    1.19
     fto
    1.18
     vété
    1.18
     thut
    1.16
     noyau
    1.15
     fta
    1.14
    Activations Density 0.057%

    No Known Activations