© 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. 6-RES-JB
    11. 6289
    Prev
    Next
    INDEX
    Explanations

    instances of the word "replace" or related terms

    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
    +0.19
    1.0%
    1272
    +0.10
    0.5%
    32
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.19
    0.03
    61
    +0.10
    0.03
    1272
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.21
    public
    -0.67
    /***
    -0.65
    ⓧ
    -0.61
    ///**
    -0.59
    ostringstream
    -0.58
    circ
    -0.57
    立
    -0.57
     earn
    -0.57
    /**
    -0.57
    POSITIVE LOGITS
     stockholm
    1.56
     lele
    1.56
     aen
    1.52
     fta
    1.51
     ftu
    1.49
     bandung
    1.48
     Juf
    1.48
     thut
    1.44
     hcm
    1.44
     wien
    1.43
    Activations Density 0.110%

    No Known Activations