© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    dates represented in a specific format

    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
    +0.25
    1.1%
    1445
    +0.07
    0.3%
    1267
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1267
    +0.25
    0.14
    1324
    +0.07
    0.12
    776
    +0.06
    0.12
    Negative Logits
    <bos>
    -2.31
    /**
    -0.98
    ⓧ
    -0.90
    
    -0.89
    <?
    -0.84
    /*
    -0.81
    /***
    -0.80
    <?
    -0.78
    /*++
    -0.70
    #![
    -0.69
    POSITIVE LOGITS
     véhic
    1.10
     maneu
    0.92
     soulign
    0.86
     affor
    0.84
     jusque
    0.82
     tantôt
    0.81
     quoique
    0.80
     pleins
    0.77
     Haci
    0.74
     préc
    0.74
    Activations Density 0.767%

    No Known Activations