© 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. 1203
    Prev
    Next
    INDEX
    Explanations

    phrases related to features and characteristics of products or services, especially in the context of tools, design, and illustrations

    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
    1.1%
    1265
    +0.13
    0.5%
    506
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.24
    0.07
    1265
    +0.13
    0.07
    1691
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.71
    ⓧ
    -1.17
    <?
    -0.92
    
    -0.85
    /**
    -0.72
    <?
    -0.70
     defray
    -0.63
     AssemblyCompany
    -0.60
    freopen
    -0.59
    isContained
    -0.58
    POSITIVE LOGITS
     aen
    1.13
     desir
    1.10
     ftu
    1.07
     fta
    1.07
     wien
    1.07
     perfon
    1.02
     matel
    1.00
     napoli
    1.00
     mef
    0.99
     milf
    0.98
    Activations Density 0.649%

    No Known Activations