© 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. 5771
    Prev
    Next
    INDEX
    Explanations

    copyright-related phrases

    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
    +0.25
    1.0%
    204
    +0.10
    0.4%
    1264
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1124
    +0.25
    0.05
    1264
    +0.10
    0.05
    537
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.76
     AssemblyCompany
    -0.73
    amoan
    -0.69
    InputBorder
    -0.67
    EndProject
    -0.67
    glBind
    -0.65
    beforeEach
    -0.61
    BindingResult
    -0.61
    toContain
    -0.61
    sendRedirect
    -0.59
    POSITIVE LOGITS
     maneu
    1.39
     milf
    1.39
     affor
    1.36
     accla
    1.33
     practition
    1.33
     pollut
    1.31
     stockholm
    1.25
     volunte
    1.21
     opport
    1.21
     attemp
    1.20
    Activations Density 0.226%

    No Known Activations