© 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. 8384
    Prev
    Next
    INDEX
    Explanations

    domains and website URLs

    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
    1842
    +0.13
    0.6%
    1177
    +0.12
    0.6%
    1705
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.13
    0.17
    1177
    +0.12
    -0.00
    227
    +0.11
    0.13
    Negative Logits
    <bos>
    -0.88
     may
    -0.71
     can
    -0.68
     established
    -0.67
    ↵↵
    -0.67
     or
    -0.66
    <?
    -0.66
     past
    -0.65
    يمكن
    -0.64
     might
    -0.63
    POSITIVE LOGITS
     wien
    1.89
     fatis
    1.84
     tanga
    1.81
     stockholm
    1.79
     territo
    1.73
     ftu
    1.73
     bandung
    1.73
     fluo
    1.71
     waer
    1.71
     myn
    1.70
    Activations Density 2.910%

    No Known Activations