© 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. 3283
    Prev
    Next
    INDEX
    Explanations

    attributes related to cost-effectiveness and efficiency

    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
    +0.35
    1.4%
    876
    +0.17
    0.7%
    1385
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.35
    -0.01
    1385
    +0.17
    0.07
    605
    +0.15
    0.01
    Negative Logits
    <bos>
    -2.19
     intersper
    -1.11
    
    -0.92
    /**
    -0.91
    ⓧ
    -0.84
     vainly
    -0.83
     rouse
    -0.82
     mustered
    -0.81
    /***
    -0.81
     inaugurate
    -0.80
    POSITIVE LOGITS
     vinci
    1.09
     croce
    1.05
     ceramica
    1.01
     ananas
    1.00
     cioc
    0.99
     lusso
    0.98
     tricot
    0.97
     paradiso
    0.96
     bandung
    0.95
     maroc
    0.94
    Activations Density 0.918%

    No Known Activations