© 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. 1944
    Prev
    Next
    INDEX
    Explanations

    phrases related to chaining or linking

    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
    +0.16
    0.9%
    1262
    +0.15
    0.9%
    1425
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.16
    0.02
    1262
    +0.15
    0.02
    1622
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.08
    else
    -0.73
    ുറ
    -0.73
    PreAuthorize
    -0.72
    setViewName
    -0.72
    IsRequired
    -0.69
    public
    -0.68
    ComponentModel
    -0.67
     else
    -0.66
    util
    -0.66
    POSITIVE LOGITS
     increa
    2.11
     impra
    1.99
     Juf
    1.93
     affor
    1.92
     unspeak
    1.88
     reluct
    1.87
     accla
    1.86
     maneu
    1.83
     inev
    1.81
     disagre
    1.81
    Activations Density 0.097%

    No Known Activations