© 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. 221
    Prev
    Next
    INDEX
    Explanations

    texts related to assigning blame or responsibility

    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
    +0.08
    0.3%
    1328
    +0.06
    0.2%
    544
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.08
    0.02
    995
    +0.06
    0.02
    768
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.45
    /***
    -0.87
    ///**
    -0.83
    /**
    -0.82
    /*
    -0.72
    fileprivate
    -0.65
    <?
    -0.61
    InkWell
    -0.60
    usercontent
    -0.59
     butterknife
    -0.58
    POSITIVE LOGITS
     fault
    2.23
     Fault
    2.08
    fault
    1.93
    Fault
    1.82
     faults
    1.73
    faults
    1.67
    Faults
    1.25
    FAULT
    1.24
     jaya
    1.17
     faulting
    1.17
    Activations Density 0.090%

    No Known Activations