© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2802
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and internal conflicts

    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
    +0.24
    1.0%
    906
    +0.18
    0.7%
    946
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.24
    0.00
    1317
    +0.18
    0.03
    946
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.11
     intersper
    -1.51
     snoopy
    -1.41
     embra
    -1.37
     milf
    -1.34
     inconce
    -1.33
     indestru
    -1.31
     encomp
    -1.29
     apprehen
    -1.29
     fuf
    -1.28
    POSITIVE LOGITS
     />";
    0.72
    />";
    0.71
     ușor
    0.67
     gând
    0.64
     destul
    0.64
     pymysql
    0.63
    imageio
    0.62
     myself
    0.61
     feeling
    0.60
    ătoare
    0.60
    Activations Density 0.616%

    No Known Activations