© 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. 776
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1604
    +0.09
    0.3%
    1385
    +0.08
    0.3%
    883
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.09
    0.04
    690
    +0.08
    0.04
    883
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.89
    <?
    -0.76
    ⓧ
    -0.70
    /*
    -0.69
    
    
    -0.69
     intersper
    -0.67
    glMatrixMode
    -0.61
     endeavored
    -0.61
     interposed
    -0.60
    /**
    -0.60
    POSITIVE LOGITS
     acne
    1.63
     wrinkles
    1.45
     pimples
    1.38
    Acne
    1.33
     Acne
    1.30
     wrinkle
    1.20
     cellulite
    1.16
     beard
    1.14
    acne
    1.13
     blemishes
    1.13
    Activations Density 0.191%

    No Known Activations