© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 254
    Prev
    Next
    INDEX
    Explanations

    references to conflict and casualties in Syria

    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
    +0.28
    1.1%
    1842
    +0.14
    0.6%
    1499
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1394
    +0.28
    0.06
    1499
    +0.14
    0.08
    939
    +0.11
    0.07
    Negative Logits
    <bos>
    -3.17
     ModelRenderer
    -0.64
    ⓧ
    -0.60
     mergeFrom
    -0.56
    ///**
    -0.56
    <!--
    
    -0.54
     spie
    -0.53
    IsMutable
    -0.53
     memorize
    -0.53
    estacks
    -0.53
    POSITIVE LOGITS
     tucson
    1.07
     orlando
    1.06
     Shakspeare
    1.06
     soulign
    1.06
     stockholm
    1.05
     affor
    1.04
     Manufact
    1.03
     véhic
    1.01
     volunte
    1.00
     beverly
    1.00
    Activations Density 0.777%

    No Known Activations