© 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. 2503
    Prev
    Next
    INDEX
    Explanations

    dates expressed in text 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
    78
    +0.09
    0.3%
    689
    +0.09
    0.3%
    1351
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    970
    +0.09
    0.06
    1992
    +0.09
    0.05
    1351
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.20
    HasIndex
    -0.72
    contentLoaded
    -0.72
    <tfoot>
    -0.71
     jsPsych
    -0.71
    featureID
    -0.66
    export
    -0.65
    webElementXpaths
    -0.65
    CreateMap
    -0.65
    ModelBuilder
    -0.64
    POSITIVE LOGITS
     maneu
    1.61
     indestru
    1.57
     considér
    1.54
     quoique
    1.50
     impra
    1.48
     impractica
    1.46
     reluct
    1.45
     véhic
    1.45
     excru
    1.45
     affor
    1.43
    Activations Density 0.117%

    No Known Activations