© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    text related to education, learning, or information sharing

    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
    0.8%
    636
    +0.09
    0.4%
    1376
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.22
    0.06
    1372
    +0.09
    0.06
    1803
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.17
    ⓧ
    -0.58
    Demografía
    -0.55
    ///**
    -0.55
    deinit
    -0.55
     enshr
    -0.54
    <tfoot>
    -0.53
     mobilize
    -0.53
     inaugurate
    -0.52
    Referanser
    -0.52
    POSITIVE LOGITS
     pylab
    1.24
     pymysql
    1.16
     unlaw
    1.08
     smtplib
    1.05
     electrica
    1.00
     pymongo
    1.00
     sappi
    0.94
     pleins
    0.94
     heapq
    0.93
     actionTypes
    0.92
    Activations Density 1.061%

    No Known Activations