© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2193
    Prev
    Next
    INDEX
    Explanations

    phrases related to featured content or highlights in documents

    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
    +0.24
    1.1%
    866
    +0.13
    0.6%
    687
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    866
    +0.24
    0.02
    990
    +0.13
    0.03
    699
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.39
    createCanvas
    -0.79
    toBe
    -0.71
    BeforeMethod
    -0.70
    public
    -0.69
    string
    -0.69
    stackrel
    -0.68
    set
    -0.67
    switch
    -0.67
    else
    -0.66
    POSITIVE LOGITS
     maneu
    2.21
     increa
    2.17
     guarante
    2.05
     affor
    1.96
     disagre
    1.95
     wherea
    1.93
     fuf
    1.93
     strick
    1.93
     alre
    1.92
     inev
    1.90
    Activations Density 0.100%

    No Known Activations