© 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. 5074
    Prev
    Next
    INDEX
    Explanations

    religious references and messages about devotion and purification

    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
    0.8%
    1842
    +0.11
    0.4%
    184
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.22
    0.05
    1317
    +0.11
    0.05
    509
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.70
    ⓧ
    -1.06
    <?
    -0.89
    /**
    -0.88
    
    -0.80
    glPushMatrix
    -0.76
    toMatch
    -0.71
    queryInterface
    -0.70
     AssemblyTitle
    -0.66
    glEnd
    -0.66
    POSITIVE LOGITS
     stockholm
    1.74
     volunte
    1.69
     emphat
    1.68
     practition
    1.67
     affor
    1.66
     wien
    1.66
     aen
    1.61
     strick
    1.59
     maneu
    1.58
     lara
    1.56
    Activations Density 0.213%

    No Known Activations