© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 353
    Prev
    Next
    INDEX
    Explanations

    numerical representations such as years, figures, and statistics

    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
    0.4%
    687
    +0.10
    0.4%
    486
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.11
    0.04
    559
    +0.10
    0.04
    814
    +0.08
    0.03
    Negative Logits
    <bos>
    -0.90
    ⓧ
    -0.70
    
    -0.68
    ുറ
    -0.62
    <?
    -0.60
    <?
    -0.59
    //{
    -0.57
    ੰ
    -0.56
     may
    -0.56
    ਿੱ
    -0.55
    POSITIVE LOGITS
     maneu
    1.76
     increa
    1.59
     depic
    1.51
     stockholm
    1.49
     suscep
    1.45
     effe
    1.45
     emphat
    1.44
     disreg
    1.44
     guarante
    1.42
     inev
    1.41
    Activations Density 0.128%

    No Known Activations