© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    terms related to team standings and tournament qualifications in sports

    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
    +0.28
    1.0%
    599
    +0.09
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.28
    0.06
    1551
    +0.09
    0.03
    455
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.92
    struct
    -0.90
    queryInterface
    -0.89
    const
    -0.87
    public
    -0.85
    建
    -0.84
    void
    -0.81
    protected
    -0.80
    交
    -0.80
    namespace
    -0.79
    POSITIVE LOGITS
     maneu
    3.08
     accla
    3.06
     increa
    3.00
     inev
    2.94
     stockholm
    2.92
     reluct
    2.90
     affor
    2.90
     emphat
    2.89
     volunte
    2.88
     impra
    2.85
    Activations Density 0.655%

    No Known Activations