© 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. 4036
    Prev
    Next
    INDEX
    Explanations

    phrases related to excavation or searching

    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
    871
    +0.15
    0.8%
    874
    +0.14
    0.7%
    82
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.15
    0.03
    1872
    +0.14
    0.03
    82
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.69
    ⓧ
    -0.72
    const
    -0.64
    IonicModule
    -0.63
    座
    -0.62
     reduce
    -0.62
    return
    -0.62
    StateList
    -0.62
    <strong>
    -0.62
    {
    -0.60
    POSITIVE LOGITS
     impra
    1.70
     unwarran
    1.68
     ecru
    1.63
     impractica
    1.62
     maneu
    1.60
     indestru
    1.57
     disagre
    1.57
     increa
    1.55
     disreg
    1.55
     inconce
    1.54
    Activations Density 0.145%

    No Known Activations