© 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. 8500
    Prev
    Next
    INDEX
    Explanations

    references to specific model car parts and related hobbyist terms

    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
    1741
    +0.16
    0.7%
    1622
    +0.13
    0.5%
    11
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.16
    0.02
    690
    +0.13
    0.09
    227
    +0.11
    0.11
    Negative Logits
    <bos>
    -2.44
    více
    -0.74
    ineno
    -0.67
    USTAIN
    -0.67
    osexual
    -0.67
    SequentialGroup
    -0.66
    <>
    -0.65
    נטרנט
    -0.65
    citenamefont
    -0.64
    otheby
    -0.64
    POSITIVE LOGITS
     Schrö
    1.67
     Juf
    1.60
     Strukt
    1.53
     meis
    1.51
     saar
    1.50
     Khart
    1.50
     kristal
    1.49
     optik
    1.43
     Nö
    1.43
     kram
    1.42
    Activations Density 1.230%

    No Known Activations