© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 699
    Prev
    Next
    INDEX
    Explanations

    mentions of colors in relation to products or objects

    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
    1044
    +0.10
    0.3%
    395
    +0.09
    0.3%
    1974
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.10
    0.03
    1626
    +0.09
    0.02
    668
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.93
    
    -0.71
    /*
    -0.70
    itemBuilder
    -0.67
    AnchorTagHelper
    -0.66
    glPushMatrix
    -0.63
    glBegin
    -0.61
    AdapterFactory
    -0.61
    <tfoot>
    -0.60
    bindParam
    -0.59
    POSITIVE LOGITS
     shade
    2.75
     Shade
    2.44
     shades
    2.31
    shade
    2.26
    Shade
    2.17
    shades
    2.07
     Shades
    2.07
    Shades
    1.87
     shading
    1.81
     shaded
    1.76
    Activations Density 0.108%

    No Known Activations