© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1592
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms related to specific measurements, systems, or functions

    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
    1896
    +0.16
    0.7%
    50
    +0.15
    0.7%
    1141
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.06
    678
    +0.15
    0.05
    876
    +0.14
    -0.01
    Negative Logits
    <bos>
    -1.81
     tsl
    -1.03
     zc
    -1.02
     sml
    -1.01
     nmax
    -0.97
     pcx
    -0.93
    <^
    -0.92
    ceff
    -0.91
    «<
    -0.90
     tst
    -0.88
    POSITIVE LOGITS
     incess
    1.13
     noblesse
    0.94
     Manufact
    0.93
     ados
    0.90
     sord
    0.87
     bourgeo
    0.86
     tass
    0.85
     utop
    0.85
     vernac
    0.85
     eccl
    0.85
    Activations Density 0.252%

    No Known Activations