© 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. 3875
    Prev
    Next
    INDEX
    Explanations

    terms related to political conflict and regions of tension

    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
    +0.24
    1.0%
    1842
    +0.17
    0.7%
    1870
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.24
    0.07
    1870
    +0.17
    0.07
    1438
    +0.11
    0.09
    Negative Logits
    <bos>
    -2.59
     succede
    -1.18
     voleva
    -1.13
    ⓧ
    -1.07
     vorrei
    -1.06
     solidar
    -1.06
     purtroppo
    -1.02
    <?
    -1.01
     adesso
    -1.00
     stiamo
    -1.00
    POSITIVE LOGITS
     clô
    0.90
     cimetière
    0.84
     écout
    0.82
     vecteur
    0.80
     ErrorCode
    0.80
     TokenType
    0.77
     malheureux
    0.77
     épu
    0.77
     déplo
    0.77
     DataType
    0.76
    Activations Density 1.093%

    No Known Activations