© 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. 4206
    Prev
    Next
    INDEX
    Explanations

    references to video games and gaming culture

    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
    1.0%
    1013
    +0.12
    0.4%
    1553
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.27
    0.11
    1013
    +0.12
    0.12
    284
    +0.08
    0.08
    Negative Logits
    <bos>
    -2.21
     encomp
    -1.08
     intersper
    -1.06
     ?...
    -1.04
    /***
    -0.99
     fuf
    -0.97
     fep
    -0.96
     fte
    -0.96
     !...
    -0.95
     inder
    -0.94
    POSITIVE LOGITS
     pymysql
    0.81
    mistak
    0.72
    relenting
    0.70
     OrderedDict
    0.67
     smtplib
    0.65
    wavering
    0.64
    numericUpDown
    0.61
    thinkable
    0.61
     AssertionError
    0.60
     psycopg
    0.60
    Activations Density 0.970%

    No Known Activations