© 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. 344
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "like."

    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
    +0.26
    1.1%
    1323
    +0.13
    0.6%
    1637
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.26
    0.05
    1637
    +0.13
    0.04
    1565
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.59
    ⓧ
    -0.77
     del
    -0.62
     bus
    -0.62
     end
    -0.61
    ref
    -0.61
    营
    -0.61
     v
    -0.61
     continue
    -0.60
    ,
    -0.59
    POSITIVE LOGITS
     wien
    1.60
     impra
    1.59
     maneu
    1.56
     thut
    1.54
     increa
    1.53
     affor
    1.53
     maroc
    1.50
     guarante
    1.49
     effe
    1.49
     impractica
    1.48
    Activations Density 0.072%

    No Known Activations