© 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. 4826
    Prev
    Next
    INDEX
    Explanations

    action verbs that imply performing, controlling, or manipulating tasks

    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
    +0.23
    0.9%
    752
    +0.16
    0.6%
    1842
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.23
    0.06
    1533
    +0.16
    0.04
    1984
    +0.15
    0.07
    Negative Logits
    <bos>
    -2.84
    errHandler
    -0.80
    SequentialGroup
    -0.80
    didSet
    -0.77
    webElementXpaths
    -0.76
    JspWriter
    -0.75
    afterEach
    -0.72
    Kjelder
    -0.72
    beforeEach
    -0.72
    PerformLayout
    -0.70
    POSITIVE LOGITS
     véhic
    1.68
     ecru
    1.66
     impra
    1.65
     maneu
    1.60
     Juf
    1.60
     affor
    1.60
     increa
    1.59
     stockholm
    1.57
     hcm
    1.51
     délib
    1.51
    Activations Density 0.747%

    No Known Activations