© 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. 322
    Prev
    Next
    INDEX
    Explanations

    announcement texts with specific event details and invitation language

    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
    +0.22
    0.9%
    2019
    +0.11
    0.4%
    752
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    600
    +0.22
    0.06
    1659
    +0.11
    0.06
    1263
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.51
    ⓧ
    -1.04
    /**
    -1.03
    <?
    -1.03
    
    -0.97
    /***
    -0.88
    /*
    -0.84
    <?
    -0.81
     disbur
    -0.74
    /*!
    -0.72
    POSITIVE LOGITS
     seksi
    1.11
     keramik
    1.00
     marte
    0.97
     silikon
    0.96
     kafe
    0.95
     nomine
    0.89
     santiago
    0.88
     catég
    0.87
     kredi
    0.87
     maroc
    0.87
    Activations Density 0.061%

    No Known Activations