© 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. 2281
    Prev
    Next
    INDEX
    Explanations

    citations or references in a document

    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
    +0.19
    0.9%
    1677
    +0.17
    0.8%
    1262
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1677
    +0.19
    0.03
    645
    +0.17
    0.02
    1262
    +0.16
    0.02
    Negative Logits
    <bos>
    -2.57
     rehabilitate
    -0.72
     disbur
    -0.68
    ⓧ
    -0.66
     modernize
    -0.66
     defray
    -0.64
     etmeye
    -0.62
     ratify
    -0.61
     consolidate
    -0.61
     displace
    -0.59
    POSITIVE LOGITS
     et
    0.96
     Et
    0.92
     éto
    0.87
     véhic
    0.86
     délib
    0.84
     ET
    0.81
     épu
    0.81
     prét
    0.78
    et
    0.78
    Et
    0.78
    Activations Density 0.031%

    No Known Activations