© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2049
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and related constructs about existence or condition

    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
    +0.39
    1.9%
    478
    +0.16
    0.7%
    2019
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.39
    0.11
    1023
    +0.16
    0.09
    478
    +0.13
    0.08
    Negative Logits
    <bos>
    -3.10
     which
    -0.64
     that
    -0.58
     these
    -0.56
    ,
    -0.56
     if
    -0.56
     this
    -0.56
     and
    -0.56
     some
    -0.55
     or
    -0.54
    POSITIVE LOGITS
     stockholm
    1.39
     lamborghini
    1.28
     lidl
    1.28
     sappi
    1.27
     desir
    1.24
     effe
    1.21
     chrysler
    1.18
     pixar
    1.17
     poichè
    1.17
     tucson
    1.17
    Activations Density 0.724%

    No Known Activations