© 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. 4144
    Prev
    Next
    INDEX
    Explanations

    moments in text where a pause or a reflective moment is mentioned

    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
    +0.17
    0.6%
    680
    +0.10
    0.4%
    1013
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.17
    0.05
    542
    +0.10
    0.03
    56
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.15
    /***
    -0.98
    <?
    -0.96
    ⓧ
    -0.92
    
    -0.91
     intersper
    -0.86
    /**
    -0.86
    <?
    -0.79
    /*!
    -0.73
     encomp
    -0.71
    POSITIVE LOGITS
     pausa
    0.81
     pause
    0.76
     maske
    0.75
     duran
    0.73
     durs
    0.71
     kask
    0.71
     kram
    0.70
    requently
    0.70
     stop
    0.70
    requent
    0.68
    Activations Density 0.307%

    No Known Activations