© 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. 3025
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases indicating hypothetical situations

    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
    +0.33
    1.6%
    404
    +0.12
    0.5%
    341
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.33
    0.10
    1265
    +0.12
    0.06
    1323
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.81
    ⓧ
    -0.71
    /***
    -0.62
    ///**
    -0.62
    protected
    -0.62
    <?
    -0.60
    HasColumnType
    -0.58
    createQuery
    -0.56
    addComponent
    -0.55
    .
    -0.55
    POSITIVE LOGITS
     accla
    1.51
     Juf
    1.43
     quoique
    1.41
     Manufact
    1.38
     Minang
    1.33
     Confe
    1.33
     volunte
    1.32
     disgra
    1.31
     thut
    1.31
     NTIS
    1.30
    Activations Density 0.185%

    No Known Activations