© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 415
    Prev
    Next
    INDEX
    Explanations

    instances of the word "got" and its variations in context

    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
    +0.26
    1.4%
    1562
    +0.17
    0.9%
    1472
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1562
    +0.26
    0.06
    1472
    +0.17
    0.04
    405
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.50
    Portály
    -0.71
    CreateIndex
    -0.66
    DataMember
    -0.66
    Demografia
    -0.66
    .
    -0.65
    mm
    -0.64
    public
    -0.64
    日
    -0.64
    getLastName
    -0.64
    POSITIVE LOGITS
     impra
    2.06
     maneu
    2.03
     increa
    1.93
     accla
    1.92
     stockholm
    1.90
     reluct
    1.89
     emphat
    1.86
     affor
    1.86
     disagre
    1.84
     unwarran
    1.84
    Activations Density 0.058%

    No Known Activations