© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4197
    Prev
    Next
    INDEX
    Explanations

    information related to a particular individual's biography and achievements

    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
    845
    +0.21
    1.2%
    1967
    +0.19
    1.1%
    1705
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    845
    +0.21
    0.18
    2016
    +0.19
    0.16
    1705
    +0.18
    0.11
    Negative Logits
    <bos>
    -3.57
    /**
    -1.03
    /*
    -0.97
    ⓧ
    -0.86
    /*++
    -0.83
    <?
    -0.83
    #![
    -0.77
    
    -0.73
    Transcripción
    -0.67
    Transkript
    -0.65
    POSITIVE LOGITS
     Minang
    1.65
     bandung
    1.57
     jaya
    1.56
     Juf
    1.49
     jawa
    1.47
     Keny
    1.41
     lele
    1.39
     kasa
    1.38
     dises
    1.37
     seksi
    1.34
    Activations Density 9.550%

    No Known Activations