© 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. 3942
    Prev
    Next
    INDEX
    Explanations

    references to specific sequels or parts of a cinematic series

    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
    +0.21
    1.2%
    1265
    +0.15
    0.8%
    1896
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1472
    +0.21
    0.02
    624
    +0.15
    0.02
    1265
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.74
    ItemBackground
    -0.71
    <?
    -0.70
    memoized
    -0.70
    pod
    -0.69
    /*---
    -0.69
    TextHelper
    -0.68
    messageInfo
    -0.66
    ẵ
    -0.66
    PageRoute
    -0.65
    POSITIVE LOGITS
     affor
    2.08
     disagre
    2.01
     increa
    1.96
     impra
    1.94
     maneu
    1.84
     emphat
    1.83
     inappro
    1.81
     uninten
    1.78
     shenan
    1.77
     guarante
    1.75
    Activations Density 0.050%

    No Known Activations