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

    Neuronpedia

    Jacobian LensNEW
    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. 357
    Prev
    Next
    INDEX
    Explanations

    restaurant or food-related terms marked as 'signature.'

    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
    1178
    +0.08
    0.3%
    1757
    +0.08
    0.3%
    1492
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2040
    +0.08
    0.02
    1494
    +0.08
    0.03
    1690
    +0.08
    0.03
    Negative Logits
    ⓧ
    -0.83
    <bos>
    -0.74
    /***
    -0.67
    /*
    -0.63
     conquête
    -0.62
    ///**
    -0.60
    /**
    -0.59
     avoid
    -0.56
     encourage
    -0.55
    //
    -0.52
    POSITIVE LOGITS
     signature
    2.82
     signatures
    2.55
     Signature
    2.54
    signature
    2.51
     Signatures
    2.38
    Signature
    2.29
     SIGNATURE
    2.28
    signatures
    2.06
    SIGNATURE
    1.87
    Signatures
    1.83
    Activations Density 0.147%

    No Known Activations