© 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. 1213
    Prev
    Next
    INDEX
    Explanations

    dialogue and text indicating interactions among users in an online forum setting

    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
    +0.49
    2.5%
    752
    +0.08
    0.4%
    1577
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.49
    0.12
    1493
    +0.08
    0.15
    1093
    +0.08
    0.15
    Negative Logits
    <bos>
    -1.79
    //
    -0.76
    public
    -0.74
    ///
    -0.73
    /**
    -0.70
    加
    -0.68
    /*
    -0.67
    ⓧ
    -0.67
    -0.67
    <!--
    -0.66
    POSITIVE LOGITS
     accla
    2.42
     affor
    2.27
     maneu
    2.19
     increa
    2.18
     inev
    2.17
     emphat
    2.10
     lele
    2.07
     volunte
    2.06
     Juf
    2.05
     opport
    2.04
    Activations Density 3.192%

    No Known Activations