© 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. 4654
    Prev
    Next
    INDEX
    Explanations

    references to hostile environments or actions

    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
    0.9%
    1145
    +0.16
    0.8%
    1778
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1145
    +0.17
    0.02
    1778
    +0.16
    0.01
    2030
    +0.11
    0.01
    Negative Logits
    <bos>
    -2.84
    addPreferredGap
    -0.72
     do
    -0.72
    StoreMessageInfo
    -0.71
    المل
    -0.71
    EndContext
    -0.70
    Vegeu
    -0.70
     did
    -0.68
    mergeFrom
    -0.67
    IsRequired
    -0.66
    POSITIVE LOGITS
     frankfurt
    1.93
     stockholm
    1.87
     wien
    1.87
     fta
    1.86
     ftu
    1.82
     bordeaux
    1.82
     lamborghini
    1.80
     fte
    1.75
     jaya
    1.74
     dises
    1.73
    Activations Density 0.042%

    No Known Activations