© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4979
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Ross."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    866
    +0.20
    1.3%
    50
    +0.16
    1.0%
    1053
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    866
    +0.20
    0.02
    1053
    +0.16
    0.02
    420
    +0.16
    0.02
    Negative Logits
    <bos>
    -2.36
    char
    -0.73
    const
    -0.73
    def
    -0.71
    enumerate
    -0.70
    var
    -0.68
    MergeFrom
    -0.68
    ContentAlignment
    -0.68
    ParallelGroup
    -0.68
    Demografia
    -0.67
    POSITIVE LOGITS
     ftu
    2.06
     Minang
    2.04
     maneu
    2.02
     increa
    2.02
     bandung
    1.99
     fta
    1.99
     disagre
    1.95
     thut
    1.92
     guarante
    1.91
     impra
    1.90
    Activations Density 0.030%

    No Known Activations