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

    Neuronpedia

    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. 6003
    Prev
    Next
    INDEX
    Explanations

    information related to infrastructure, engineering, and organizations involved in civil engineering initiatives

    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
    1.3%
    2019
    +0.18
    1.1%
    1967
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.22
    0.10
    1967
    +0.18
    0.09
    2019
    +0.18
    0.08
    Negative Logits
    <bos>
    -3.86
    ⓧ
    -1.43
    /**
    -1.24
    
    -1.12
    <?
    -1.07
    /***
    -0.95
    /*
    -0.95
    PerformLayout
    -0.85
     springfox
    -0.83
    /*++
    -0.76
    POSITIVE LOGITS
     bandung
    1.18
     véhic
    1.03
     corrom
    1.03
     surabaya
    0.98
     multicolore
    0.95
     migli
    0.95
     hcm
    0.94
     Minang
    0.93
     lele
    0.92
     silikon
    0.91
    Activations Density 0.592%

    No Known Activations