© 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. 2519
    Prev
    Next
    INDEX
    Explanations

    keywords related to open source technologies and software development

    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
    971
    +0.06
    0.2%
    50
    +0.06
    0.2%
    1810
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1066
    +0.06
    0.02
    1284
    +0.06
    0.02
    499
    +0.06
    0.02
    Negative Logits
     dras
    -0.56
    /*++
    -0.54
    //{
    -0.51
     immediately
    -0.51
    stums
    -0.50
    ✉
    -0.50
    ೊ
    -0.50
     directly
    -0.50
     must
    -0.49
     provide
    -0.49
    POSITIVE LOGITS
     maneu
    1.11
     fatis
    1.05
     unce
    1.02
     volunte
    1.01
     affor
    1.00
     Juf
    0.99
     embodi
    0.99
     ftre
    0.98
     bourg
    0.98
    <^
    0.96
    Activations Density 0.175%

    No Known Activations