© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    instances of the word "complainant."

    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
    313
    +0.08
    0.2%
    874
    +0.07
    0.2%
    1052
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.02
    1343
    +0.07
    0.07
    184
    +0.07
    0.03
    Negative Logits
     пів
    -1.01
     використо
    -0.99
     per
    -0.95
    个
    -0.95
     far
    -0.94
    Sprintf
    -0.94
    AspNetCore
    -0.94
    Asimismo
    -0.93
     можливо
    -0.93
     CURLOPT
    -0.93
    POSITIVE LOGITS
     reluct
    4.21
     increa
    4.20
     affor
    4.07
     inev
    4.01
     maneu
    4.01
     disagre
    3.94
     encomp
    3.92
     impra
    3.86
     guarante
    3.82
     depic
    3.82
    Activations Density 0.431%

    No Known Activations