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

    Neuronpedia

    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. 6043
    Prev
    Next
    INDEX
    Explanations

    keywords related to business processes optimization and digital marketing strategies

    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
    +0.24
    1.0%
    1403
    +0.13
    0.6%
    478
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.24
    0.06
    1253
    +0.13
    0.03
    1533
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.96
     intersper
    -2.13
     encomp
    -1.72
     shenan
    -1.70
     indestru
    -1.65
     reluct
    -1.53
     unspeak
    -1.47
     depic
    -1.44
     inconce
    -1.42
     Mlle
    -1.41
    POSITIVE LOGITS
     utop
    1.15
     bunda
    1.14
     parati
    1.12
     lapto
    1.04
     tenda
    1.04
     torba
    1.04
     lampa
    1.02
     rú
    1.02
     ortop
    1.01
     pól
    0.99
    Activations Density 4.299%

    No Known Activations