© 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. 6-RES-JB
    11. 6303
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to legal or law enforcement contexts

    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
    1974
    +0.16
    0.9%
    966
    +0.16
    0.9%
    1618
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.05
    1343
    +0.16
    0.07
    1575
    +0.14
    0.04
    Negative Logits
     intersper
    -0.87
    <bos>
    -0.85
     unspeak
    -0.81
     encomp
    -0.78
     impelled
    -0.70
     enshr
    -0.69
     interposed
    -0.68
     amass
    -0.65
     disreg
    -0.65
     indescri
    -0.65
    POSITIVE LOGITS
    Bobby
    0.79
     Bobby
    0.76
     NKC
    0.73
    bobby
    0.70
     répon
    0.68
    Toe
    0.66
     Heiden
    0.63
    coration
    0.63
     padx
    0.62
    úrese
    0.62
    Activations Density 0.780%

    No Known Activations