© 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. 4672
    Prev
    Next
    INDEX
    Explanations

    phrases containing the verb "be" in various forms and 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
    +0.36
    1.8%
    1937
    +0.12
    0.6%
    122
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.36
    0.05
    122
    +0.12
    0.05
    1323
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.46
     which
    -0.61
     and
    -0.58
    ,
    -0.58
    9
    -0.55
     I
    -0.55
     (
    -0.54
    -
    -0.54
    <eos>
    -0.53
    2
    -0.53
    POSITIVE LOGITS
     applau
    1.18
     shopee
    1.16
     emper
    1.12
     Muhamma
    1.08
     Minang
    1.07
    !!</
    1.07
     🔥🔥
    1.07
     stockholm
    1.05
     ankara
    1.02
     dises
    1.02
    Activations Density 0.125%

    No Known Activations