© 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. 298
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions related to relationships or connections in context

    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
    +0.17
    0.6%
    1842
    +0.15
    0.6%
    1343
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1224
    +0.17
    0.06
    764
    +0.15
    0.04
    394
    +0.14
    0.06
    Negative Logits
    <bos>
    -3.04
    .
    -0.75
    /**
    -0.71
    ,
    -0.70
      
    -0.66
    var
    -0.64
    源
    -0.62
     de
    -0.61
    hoeddwyd
    -0.61
     and
    -0.60
    POSITIVE LOGITS
     cabrio
    1.54
     kosme
    1.51
     ananas
    1.47
     sappi
    1.42
     Ottobre
    1.40
     silikon
    1.40
     praktik
    1.39
     alkoh
    1.39
     kafe
    1.37
     applau
    1.36
    Activations Density 0.375%

    No Known Activations