© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 8814
    Prev
    Next
    INDEX
    Explanations

    a specific sequence of words introducing a list

    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
    674
    +0.14
    1.3%
    1741
    +0.07
    0.6%
    478
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    674
    +0.14
    0.05
    1523
    +0.07
    0.15
    108
    +0.05
    0.17
    Negative Logits
     nazis
    -1.00
     défaite
    -0.95
     massacres
    -0.95
     incendi
    -0.95
     alkoh
    -0.93
     Socialista
    -0.92
     despotism
    -0.91
     tortura
    -0.90
     revan
    -0.90
     comunista
    -0.88
    POSITIVE LOGITS
    <bos>
    16.31
    GEBURTSDATUM
    2.33
    تقاوى
    2.27
    expandindo
    2.27
     betweenstory
    2.19
    Autoritní
    2.13
     Administrativna
    2.13
     Италијани
    1.99
     Мексичка
    1.97
     kaarangay
    1.95
    Activations Density 0.151%

    No Known Activations