© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    elements related to game components and their organization

    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
    1705
    +0.23
    1.1%
    1967
    +0.21
    1.0%
    1842
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.23
    0.11
    2016
    +0.21
    0.11
    845
    +0.18
    0.10
    Negative Logits
    <bos>
    -2.06
    Lmfao
    -0.97
    Hahah
    -0.96
    <?
    -0.89
    /**
    -0.83
    /*
    -0.79
    Ikr
    -0.78
    ⓧ
    -0.78
    Noice
    -0.76
    #![
    -0.76
    POSITIVE LOGITS
     jawa
    0.89
     kasa
    0.79
     seksi
    0.78
     kaos
    0.73
     panik
    0.73
     jaya
    0.72
    󠁿
    0.72
     bandung
    0.71
     lele
    0.71
     babi
    0.69
    Activations Density 2.729%

    No Known Activations