© 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. 3852
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "come" and its variations

    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
    +0.28
    1.4%
    405
    +0.15
    0.8%
    1921
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.28
    0.09
    1562
    +0.15
    0.06
    1921
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.45
    ⓧ
    -0.65
    /*
    -0.57
    hub
    -0.57
    HasIndex
    -0.55
     дописавши
    -0.53
    座
    -0.53
     Hub
    -0.53
    setDo
    -0.53
    bot
    -0.52
    POSITIVE LOGITS
     accla
    1.56
     unwarran
    1.44
     maneu
    1.40
     tupperware
    1.37
     reluct
    1.36
     swarovski
    1.35
     impra
    1.34
     disagre
    1.32
     unlaw
    1.32
     affor
    1.31
    Activations Density 0.093%

    No Known Activations