© 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. 8520
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific disciplines and their methodologies

    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
    1870
    +0.13
    0.6%
    1325
    +0.13
    0.6%
    1705
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.13
    0.04
    1125
    +0.13
    0.04
    1363
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.24
     AssemblyCompany
    -0.80
    ⓧ
    -0.78
    HasIndex
    -0.71
    WireFormat
    -0.70
    HasOne
    -0.69
    geslacht
    -0.69
    <?
    -0.67
    /*++
    -0.67
    Пото
    -0.66
    POSITIVE LOGITS
     ftu
    1.48
     bandung
    1.46
     thut
    1.44
     fta
    1.42
     reft
    1.42
     levis
    1.39
     increa
    1.38
     aen
    1.37
     squa
    1.36
     fto
    1.36
    Activations Density 0.423%

    No Known Activations