© 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. 2738
    Prev
    Next
    INDEX
    Explanations

    terms related to biofuels and energy sources derived from living organisms

    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%
    1842
    +0.16
    0.6%
    1967
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.35
    0.05
    876
    +0.16
    -0.02
    1385
    +0.13
    0.09
    Negative Logits
    <bos>
    -1.68
     intersper
    -1.30
     encomp
    -1.00
     depic
    -0.93
     disbur
    -0.87
     adjour
    -0.83
     endow
    -0.82
     shenan
    -0.80
    /***
    -0.80
     quitted
    -0.79
    POSITIVE LOGITS
     indispensables
    0.74
     marea
    0.74
     borsa
    0.69
     ados
    0.69
     ferie
    0.67
     citta
    0.67
     polizia
    0.65
     ajustable
    0.65
    gruntled
    0.65
     cioc
    0.65
    Activations Density 1.181%

    No Known Activations