© 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. 3175
    Prev
    Next
    INDEX
    Explanations

    webpage elements such as headings or navigation links

    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
    +0.22
    0.9%
    752
    +0.10
    0.5%
    1926
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1309
    +0.22
    0.04
    1926
    +0.10
    0.04
    868
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.57
    <?
    -0.97
    ⓧ
    -0.92
    /**
    -0.81
    /*
    -0.80
    <?
    -0.73
     immer
    -0.72
    /**
    -0.70
    
    -0.69
    /*++
    -0.69
    POSITIVE LOGITS
     affor
    2.29
     increa
    2.23
     accla
    2.14
     maneu
    2.13
     inev
    2.02
     reluct
    1.97
     volunte
    1.94
     emphat
    1.93
     impra
    1.92
     perfet
    1.89
    Activations Density 0.164%

    No Known Activations