© 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. 4655
    Prev
    Next
    INDEX
    Explanations

    URL encoded characters in a web address

    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
    1343
    +0.16
    0.6%
    732
    +0.09
    0.3%
    1443
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.03
    1716
    +0.09
    0.02
    244
    +0.08
    0.02
    Negative Logits
    <bos>
    -1.73
    /**
    -0.69
    calciatore
    -0.65
    //};
    -0.64
    aarrggbb
    -0.62
     MITCHELL
    -0.62
     EDWARDS
    -0.60
    InjectAttribute
    -0.59
     GILBERT
    -0.58
     MARSHALL
    -0.57
    POSITIVE LOGITS
     Ottobre
    1.00
     inol
    0.99
     applau
    0.98
     sappi
    0.97
     Luglio
    0.91
     chiunque
    0.91
     carrefour
    0.87
     moulin
    0.85
     Altri
    0.85
     salu
    0.83
    Activations Density 0.054%

    No Known Activations