© 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. 0-RES-JB
    11. 2549
    Prev
    Next
    INDEX
    Explanations

    references to food-related services or products, particularly those related to healthy meal deliveries and food preparation services

    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
    +0.06
    0.2%
    13
    +0.06
    0.2%
    1375
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.06
    0.09
    1363
    +0.06
    0.05
    1375
    +0.05
    0.04
    Negative Logits
    <bos>
    -0.88
    Configurer
    -0.74
    /***
    -0.67
    ActionCreators
    -0.58
    //{
    -0.56
    Sucesor
    -0.53
    bibinfo
    -0.51
        
    -0.49
    ામ
    -0.48
    BUYER
    -0.47
    POSITIVE LOGITS
     maneu
    1.09
     stockholm
    0.96
     blackpink
    0.92
     roberto
    0.90
     bandung
    0.89
     disparu
    0.89
     ricardo
    0.88
     hairc
    0.88
     jorge
    0.88
     ardour
    0.87
    Activations Density 1.314%

    No Known Activations