© 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. 1219
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases and argumentation

    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
    1276
    +0.12
    0.4%
    1472
    +0.10
    0.3%
    1187
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.03
    1276
    +0.10
    0.02
    677
    +0.09
    0.02
    Negative Logits
    <bos>
    -0.88
    ണ്ട
    -0.69
            
    -0.68
     tė
    -0.68
    -0.67
    움
    -0.67
    ,
    -0.66
     дис
    -0.66
     būtų
    -0.66
     gør
    -0.66
    POSITIVE LOGITS
     Ka
    2.48
    Ka
    2.31
     accla
    2.00
     increa
    1.99
     ka
    1.93
     effe
    1.92
     affor
    1.92
     unden
    1.89
     emphat
    1.89
     Manufact
    1.88
    Activations Density 0.143%

    No Known Activations