© 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. 2831
    Prev
    Next
    INDEX
    Explanations

    measurements, weights, and technical details within item descriptions, possibly related to antiques or artifacts

    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
    554
    +0.16
    0.9%
    645
    +0.15
    0.8%
    544
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.16
    0.03
    486
    +0.15
    0.02
    347
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.09
     intersper
    -0.87
     roberto
    -0.78
     procra
    -0.77
     chande
    -0.75
     !...
    -0.75
     rafael
    -0.74
     quitted
    -0.72
     encomp
    -0.72
     hastened
    -0.70
    POSITIVE LOGITS
     cm
    1.45
    cm
    1.41
     CM
    1.31
    CM
    1.25
    Cm
    0.94
     cms
    0.93
     centimeters
    0.92
     CMS
    0.90
    CMS
    0.90
    cms
    0.90
    Activations Density 0.341%

    No Known Activations