© 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. 1916
    Prev
    Next
    INDEX
    Explanations

    themes related to economic conditions and societal structures

    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
    394
    +0.22
    1.0%
    50
    +0.15
    0.7%
    1741
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.22
    0.15
    1870
    +0.15
    0.07
    1741
    +0.15
    -0.02
    Negative Logits
    <bos>
    -2.54
    .
    -0.94
    पया
    -0.75
    。
    -0.68
    ;
    -0.67
    ↵↵
    -0.66
    :
    -0.66
    ECONDS
    -0.65
     do
    -0.64
        
    -0.63
    POSITIVE LOGITS
     aen
    1.54
     Juf
    1.47
     hcm
    1.46
     wien
    1.44
     véhic
    1.42
     délib
    1.42
     jorge
    1.41
     levis
    1.41
     verona
    1.41
     centrif
    1.40
    Activations Density 3.009%

    No Known Activations