© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1686
    Prev
    Next
    INDEX
    Explanations

    references to executives and statements made by them

    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
    +0.22
    0.8%
    227
    +0.09
    0.3%
    198
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1474
    +0.22
    0.04
    929
    +0.09
    0.04
    344
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.77
     intersper
    -1.41
     swarovski
    -1.00
     encomp
    -0.96
     papà
    -0.95
     underval
    -0.91
     snoopy
    -0.90
     hairc
    -0.89
     shenan
    -0.88
     stickied
    -0.88
    POSITIVE LOGITS
    Manbalar
    0.81
    Dijo
    0.76
    Život
    0.71
     Strukt
    0.68
    cupertino
    0.66
    Literat
    0.66
    Especificaciones
    0.65
     }}"></
    0.65
    Čo
    0.64
     maksi
    0.63
    Activations Density 0.287%

    No Known Activations