© 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. 4668
    Prev
    Next
    INDEX
    Explanations

    measurements and capacities associated with energy production

    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
    +0.17
    0.6%
    1778
    +0.10
    0.3%
    1124
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.17
    0.04
    914
    +0.10
    0.04
    227
    +0.10
    0.06
    Negative Logits
    <bos>
    -1.90
     vainly
    -0.73
     blest
    -0.73
    isometric
    -0.72
     eqn
    -0.68
     gratify
    -0.66
     gaily
    -0.66
     démarches
    -0.64
     disarm
    -0.63
     nobler
    -0.63
    POSITIVE LOGITS
     lele
    1.43
     kaos
    1.31
     parati
    1.28
     marte
    1.27
     ananas
    1.27
     kram
    1.26
     miniatura
    1.26
     karton
    1.25
     silikon
    1.24
     jaya
    1.24
    Activations Density 0.576%

    No Known Activations