© 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. 3837
    Prev
    Next
    INDEX
    Explanations

    references to laws and legal acts

    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
    0.9%
    1961
    +0.16
    0.8%
    1404
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1565
    +0.17
    0.04
    1961
    +0.16
    0.03
    1499
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.68
     solidar
    -0.70
    intios
    -0.67
    المكان
    -0.63
    EndProject
    -0.63
    ⓧ
    -0.62
    namefont
    -0.61
    Hochspringen
    -0.59
    StoreMessageInfo
    -0.59
    SourceChecksum
    -0.57
    POSITIVE LOGITS
     disagre
    1.33
     reluct
    1.29
     disreg
    1.28
     maneu
    1.28
     impra
    1.20
     indestru
    1.18
     shenan
    1.16
     cuck
    1.16
     apprehen
    1.15
     uninten
    1.15
    Activations Density 0.133%

    No Known Activations