© 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. 4316
    Prev
    Next
    INDEX
    Explanations

    numerical values and punctuation marks, particularly periods

    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
    1967
    +0.29
    1.2%
    1343
    +0.27
    1.1%
    50
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.29
    0.07
    446
    +0.27
    0.05
    981
    +0.19
    0.05
    Negative Logits
    <bos>
    -3.33
     intersper
    -1.35
    /**
    -1.01
    ⓧ
    -0.98
     encomp
    -0.96
     gratify
    -0.95
     overcrow
    -0.94
     Мексичка
    -0.92
     endow
    -0.92
    <?
    -0.92
    POSITIVE LOGITS
     alcool
    0.70
     Contribu
    0.65
     miniatura
    0.65
     ados
    0.63
     Formato
    0.62
     tenda
    0.61
     Gestão
    0.61
     roba
    0.60
     motocic
    0.60
     acido
    0.59
    Activations Density 0.097%

    No Known Activations