© 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. 4670
    Prev
    Next
    INDEX
    Explanations

    actions related to handling and moving objects, often with a focus on packaging or placement

    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
    +0.21
    0.8%
    678
    +0.12
    0.5%
    1177
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.21
    0.06
    1531
    +0.12
    0.04
    690
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.33
    /***
    -0.84
    <>
    -0.82
    Хро
    -0.81
    ValueGenerated
    -0.78
    cout
    -0.78
    CreateIndex
    -0.76
    train
    -0.74
    glMatrixMode
    -0.74
    beforeAll
    -0.73
    POSITIVE LOGITS
     thut
    2.16
     increa
    2.08
     aen
    2.07
     maneu
    2.04
     fta
    2.00
     stockholm
    1.96
     impra
    1.95
     ftu
    1.95
     emphat
    1.93
     jurassic
    1.93
    Activations Density 0.310%

    No Known Activations