© 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. 0-RES-JB
    11. 61
    Prev
    Next
    INDEX
    Explanations

    mentions of forces, troops, and conflicts in different contexts

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.11
    0.4%
    74
    +0.04
    0.2%
    61
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    821
    +0.11
    0.04
    74
    +0.04
    0.04
    624
    +0.04
    0.04
    Negative Logits
    <bos>
    -1.71
    
    -0.78
    /***
    -0.74
    <?
    -0.71
    /**
    -0.69
    ⓧ
    -0.68
    <?
    -0.68
    public
    -0.67
    //---
    -0.66
     abolish
    -0.59
    POSITIVE LOGITS
     forces
    1.87
     Forces
    1.74
    Forces
    1.72
    forces
    1.56
     FORCES
    1.45
     Minang
    1.43
     force
    1.39
     hcm
    1.29
     nuoc
    1.26
     Force
    1.22
    Activations Density 0.104%

    No Known Activations