© 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. 6-RES-JB
    11. 2646
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and proceedings, particularly those involving interpretation of policies and court decisions

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    689
    +0.14
    0.6%
    1557
    +0.12
    0.5%
    1145
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.10
    1363
    +0.12
    0.07
    678
    +0.11
    0.08
    Negative Logits
    /**
    -0.73
     gøre
    -0.72
     trasladado
    -0.69
    <bos>
    -0.68
     betale
    -0.67
     sikre
    -0.66
    बाट
    -0.65
     mustered
    -0.64
     naudoti
    -0.63
     saada
    -0.63
    POSITIVE LOGITS
     répon
    1.06
     Refle
    1.06
     contex
    1.06
     socie
    1.02
     rafraî
    1.01
     clô
    1.01
     coû
    1.00
     robus
    1.00
     resis
    0.99
     synap
    0.98
    Activations Density 0.795%

    No Known Activations