© 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. 2730
    Prev
    Next
    INDEX
    Explanations

    themes related to life and death experiences

    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
    1343
    +0.21
    0.7%
    50
    +0.17
    0.6%
    1577
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.21
    0.10
    1978
    +0.17
    0.07
    706
    +0.08
    0.05
    Negative Logits
    <bos>
    -3.04
    SourceChecksum
    -1.21
    Personendaten
    -1.14
    Билгалдахарш
    -1.13
    EndGlobalSection
    -1.05
    TagMode
    -1.02
    SharedDtor
    -0.97
     Roskov
    -0.96
    Autoritní
    -0.92
    MessageOf
    -0.89
    POSITIVE LOGITS
     affor
    1.15
     fortn
    1.12
     shenan
    1.11
     accla
    1.11
     saar
    1.10
     strick
    1.10
     exorbit
    1.09
     contribut
    1.08
     maneu
    1.08
     meis
    1.07
    Activations Density 0.663%

    No Known Activations