© 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. 4024
    Prev
    Next
    INDEX
    Explanations

    the pronoun "it" being used in various contexts

    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
    +0.34
    1.7%
    82
    +0.13
    0.6%
    1222
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.34
    0.12
    1222
    +0.13
    0.10
    528
    +0.11
    0.10
    Negative Logits
    <bos>
    -2.57
    ⓧ
    -0.60
     Lá
    -0.59
     Võ
    -0.59
    Autoritní
    -0.56
     mena
    -0.55
     autorytatywna
    -0.55
    Lá
    -0.55
     drap
    -0.54
     perla
    -0.54
    POSITIVE LOGITS
    ;;)
    0.78
    >\<
    0.78
    :"-
    0.78
     camry
    0.77
     soulign
    0.74
    ">/
    0.73
    ">...
    0.71
     chrysler
    0.70
     it
    0.68
    It
    0.67
    Activations Density 0.505%

    No Known Activations