© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6540
    Prev
    Next
    INDEX
    Explanations

    information related to administrative services and procedures, especially in the context of trial courts

    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
    +0.34
    1.9%
    2019
    +0.14
    0.8%
    1265
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.34
    0.14
    2019
    +0.14
    0.14
    394
    +0.10
    0.12
    Negative Logits
    <bos>
    -3.82
    ⓧ
    -1.20
    <?
    -1.00
    /**
    -0.98
    
    
    -0.95
    /*
    -0.88
     AssemblyCompany
    -0.84
    uxxxx
    -0.83
    fromnode
    -0.81
    Cyfarwyddwr
    -0.79
    POSITIVE LOGITS
     affor
    2.17
     maneu
    2.17
     increa
    2.15
     impra
    2.13
     disagre
    2.02
     reluct
    2.01
     inev
    1.91
     Juf
    1.90
     accla
    1.88
     unwarran
    1.86
    Activations Density 1.549%

    No Known Activations