© 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. 775
    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
    50
    +0.08
    0.2%
    107
    +0.07
    0.2%
    1623
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.08
    0.03
    1874
    +0.07
    0.02
    304
    +0.06
    0.02
    Negative Logits
    <bos>
    -0.93
    establish
    -0.67
    Enllaços
    -0.66
     pull
    -0.65
     serve
    -0.64
    /*
    -0.64
     assist
    -0.63
    <?
    -0.62
    {~
    -0.62
    ///
    -0.60
    POSITIVE LOGITS
     maneu
    1.99
     mef
    1.86
     inev
    1.84
     effe
    1.80
     lele
    1.79
     meis
    1.79
     reluct
    1.78
     increa
    1.78
     guarante
    1.77
     Pamph
    1.77
    Activations Density 0.136%

    No Known Activations