© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4053
    Prev
    Next
    INDEX
    Explanations

    references to off-road vehicles, especially compact Land Rover models

    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
    +0.17
    0.6%
    1385
    +0.12
    0.4%
    658
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.17
    0.07
    1597
    +0.12
    0.04
    1694
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.81
    ⓧ
    -0.82
    
    -0.79
    /**
    -0.78
    <?
    -0.77
     plundered
    -0.69
     corvette
    -0.67
     hastened
    -0.67
     endeavoured
    -0.67
     defray
    -0.66
    POSITIVE LOGITS
     vinci
    1.00
     paradiso
    1.00
     montagna
    0.95
     wattpad
    0.94
     nomine
    0.93
     papà
    0.93
     frambo
    0.92
     tibi
    0.91
     croce
    0.90
     embodi
    0.90
    Activations Density 0.409%

    No Known Activations