© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6651
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations in a city

    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
    1.1%
    144
    +0.10
    0.6%
    161
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.19
    0.03
    1639
    +0.10
    0.03
    1013
    +0.09
    0.02
    Negative Logits
    <bos>
    -3.36
    ⓧ
    -1.10
    /**
    -1.05
    
    -1.02
    <?
    -1.02
    /***
    -1.01
    <?
    -0.89
    /*
    -0.85
    /*!
    -0.82
    /*++
    -0.80
    POSITIVE LOGITS
     lele
    1.47
     meis
    1.32
     ananas
    1.30
     kram
    1.23
     Juf
    1.17
     marte
    1.16
     sirop
    1.13
     saar
    1.12
     nuoc
    1.12
     kaos
    1.12
    Activations Density 0.065%

    No Known Activations