© 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. 3855
    Prev
    Next
    INDEX
    Explanations

    constructs relating to the complexities and nuances of social processes and perceptions

    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%
    1387
    +0.12
    0.5%
    1407
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.27
    0.06
    966
    +0.12
    0.04
    223
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.21
    <tfoot>
    -0.65
    Παραπομπές
    -0.53
    сылкі
    -0.52
    ोंने
    -0.51
    ///////////////
    -0.50
    ////////////
    -0.50
    WriteAttribute
    -0.50
    حوالہ
    -0.49
    ///////////
    -0.49
    POSITIVE LOGITS
     pymysql
    1.12
     pymongo
    1.05
     heapq
    0.99
     skimage
    0.95
     smtplib
    0.94
     pylab
    0.90
     swarovski
    0.88
     psycopg
    0.87
     ecru
    0.86
     panama
    0.77
    Activations Density 0.395%

    No Known Activations