© 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. 1357
    Prev
    Next
    INDEX
    Explanations

    references to the Manning family, particularly focusing on Peyton Manning

    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
    1306
    +0.15
    0.8%
    1101
    +0.13
    0.7%
    554
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.15
    0.00
    1256
    +0.13
    0.02
    1097
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.50
    djangoproject
    -0.69
    OGND
    -0.67
     صوتيه
    -0.67
     sarili
    -0.66
     تانيه
    -0.65
    Datuak
    -0.64
    Smit
    -0.60
    Mur
    -0.58
     muna
    -0.58
    POSITIVE LOGITS
     Manning
    1.62
     Hæ
    0.89
     isabel
    0.88
     gubern
    0.88
     frankfurt
    0.86
     stockholm
    0.83
     chay
    0.83
     Mâ
    0.83
     pixar
    0.83
     ricardo
    0.82
    Activations Density 0.199%

    No Known Activations