© 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. 7185
    Prev
    Next
    INDEX
    Explanations

    assertions or confirmations

    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
    +0.19
    1.0%
    478
    +0.13
    0.7%
    971
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    971
    +0.19
    0.03
    1065
    +0.13
    0.03
    893
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.08
    ⓧ
    -1.09
    /***
    -1.05
    
    -0.98
    /*!
    -0.90
    ///**
    -0.83
    <?
    -0.81
    /**
    -0.79
     endow
    -0.79
    }],
    -0.71
    POSITIVE LOGITS
     thuy
    0.93
    certainly
    0.89
     Certainly
    0.81
     gilet
    0.79
     certainly
    0.79
    asserole
    0.79
     ados
    0.79
    Certainly
    0.77
     chèvre
    0.77
     benzina
    0.76
    Activations Density 0.091%

    No Known Activations