© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 354
    Prev
    Next
    INDEX
    Explanations

    words related to financial markets, funds, and investments

    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
    50
    +0.23
    0.9%
    1385
    +0.08
    0.3%
    2045
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.23
    0.06
    2045
    +0.08
    0.04
    1216
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.63
    ⓧ
    -0.82
     Walkover
    -0.77
     AssemblyCompany
    -0.73
    PerformLayout
    -0.72
    endwhile
    -0.67
    Identyfik
    -0.66
     jsPsych
    -0.66
    uxxxx
    -0.65
    queryInterface
    -0.65
    POSITIVE LOGITS
     Minang
    1.42
     Juf
    1.40
     maneu
    1.39
     increa
    1.38
     wherea
    1.37
     bandung
    1.36
     affor
    1.35
     impra
    1.34
     Jambi
    1.33
     jaya
    1.33
    Activations Density 0.456%

    No Known Activations