© 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. 6318
    Prev
    Next
    INDEX
    Explanations

    publication-related information like DOIs, URLs, and publication details

    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%
    1018
    +0.09
    0.3%
    75
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1927
    +0.17
    0.03
    1213
    +0.09
    0.03
    685
    +0.08
    0.02
    Negative Logits
    /**
    -0.71
    ⓧ
    -0.71
    ///**
    -0.68
     "..\..\..\
    -0.63
     setObject
    -0.61
    ="#">
    -0.60
    AddField
    -0.60
    ||}
    -0.60
    addGroup
    -0.60
    }{||
    -0.59
    POSITIVE LOGITS
     affor
    1.45
     véhic
    1.44
     impra
    1.37
     pleins
    1.34
     cushi
    1.32
     accla
    1.30
     strick
    1.29
     rafra
    1.29
     vété
    1.28
     tupperware
    1.28
    Activations Density 0.036%

    No Known Activations