© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 2158
    Prev
    Next
    INDEX
    Explanations

    references to images or image-related content

    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
    0.5%
    2011
    +0.06
    0.3%
    1331
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.11
    0.04
    888
    +0.06
    0.04
    543
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.55
    ⓧ
    -0.94
     springfox
    -0.92
    <?
    -0.88
    
    
    -0.86
    /**
    -0.85
    /*
    -0.75
    /*++
    -0.72
    #![
    -0.70
    <?
    
    -0.70
    POSITIVE LOGITS
     image
    1.58
     Image
    1.51
     wien
    1.41
     aen
    1.40
     stockholm
    1.39
     meis
    1.38
    image
    1.37
     maroc
    1.35
     imago
    1.33
     franz
    1.30
    Activations Density 0.136%

    No Known Activations