© 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. 0-RES-JB
    6. 1060
    Prev
    Next
    INDEX
    Explanations

    positive affirmations and encouragements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.11
    0.4%
    397
    +0.06
    0.2%
    1451
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1757
    +0.11
    0.04
    397
    +0.06
    0.04
    1780
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.63
    ⓧ
    -0.82
    //});
    -0.74
    numerusform
    -0.71
    DoubleQuotes
    -0.70
    hline
    -0.70
    addComponent
    -0.70
    enumerate
    -0.70
    /**
    -0.70
    WaitGroup
    -0.69
    POSITIVE LOGITS
     maneu
    2.12
     affor
    2.07
     increa
    2.00
     impra
    1.97
     scrat
    1.93
     disagre
    1.90
     emphat
    1.87
     uninten
    1.85
     disreg
    1.85
     eiffel
    1.82
    Activations Density 0.252%

    No Known Activations