© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    text related to news stories or subjects found in an online blog

    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
    1.1%
    1438
    +0.10
    0.5%
    1356
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.23
    -0.08
    453
    +0.10
    0.19
    1539
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.13
    ,
    -0.83
    <?
    -0.77
     and
    -0.75
     or
    -0.70
    
    -0.66
     ,
    -0.65
    /***
    -0.65
     but
    -0.64
    <?
    -0.63
    POSITIVE LOGITS
     lidl
    1.44
     stockholm
    1.33
     wien
    1.33
     nece
    1.25
     unden
    1.24
     affor
    1.23
     lamborghini
    1.22
     maroc
    1.21
     lyon
    1.21
     maneu
    1.19
    Activations Density 7.066%

    No Known Activations