© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4782
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" in various contexts

    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
    +0.31
    1.6%
    1047
    +0.13
    0.6%
    554
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1047
    +0.31
    0.06
    554
    +0.13
    0.06
    596
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.30
    /***
    -0.74
    ⓧ
    -0.57
     بتاريخ
    -0.55
    <?
    -0.53
    lateinit
    -0.52
    BC
    -0.50
     Stein
    -0.49
     Anne
    -0.49
     Jones
    -0.49
    POSITIVE LOGITS
     chrysler
    1.17
     mitsubishi
    1.16
     peugeot
    1.15
     lamborghini
    1.13
     isuzu
    1.12
     bosch
    1.08
     husqvarna
    1.07
     kawasaki
    1.07
     beverly
    1.05
     maneu
    1.04
    Activations Density 0.086%

    No Known Activations