© 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. 4212
    Prev
    Next
    INDEX
    Explanations

    locations and amenities in a property description

    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
    +0.18
    0.7%
    1013
    +0.15
    0.6%
    1385
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.18
    0.08
    1385
    +0.15
    0.07
    1971
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.70
    ⓧ
    -1.21
    <?
    -1.16
    /**
    -1.06
    
    -1.06
    /***
    -0.95
    <?
    -0.92
    /*
    -0.82
    RemoveField
    -0.76
     AssemblyCompany
    -0.74
    POSITIVE LOGITS
     patio
    0.82
     uchiha
    0.77
     garten
    0.74
     caccia
    0.74
     cavallo
    0.73
     allé
    0.73
    Outdoor
    0.72
     nuoc
    0.72
     Intere
    0.72
     saar
    0.72
    Activations Density 0.459%

    No Known Activations