© 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. 2103
    Prev
    Next
    INDEX
    Explanations

    phrases related to archives or specific dates

    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
    +0.10
    0.3%
    16
    +0.08
    0.2%
    1473
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1206
    +0.10
    0.04
    924
    +0.08
    0.04
    1716
    +0.07
    0.04
    Negative Logits
     jät
    -0.65
     neum
    -0.62
     hial
    -0.58
     nõ
    -0.58
     läm
    -0.57
     koke
    -0.56
     melat
    -0.56
     kilomet
    -0.55
     pü
    -0.55
    hnung
    -0.55
    POSITIVE LOGITS
     milf
    1.03
     accla
    1.02
     madonna
    0.90
     practition
    0.90
     snoopy
    0.85
     affor
    0.83
     maneu
    0.82
     michelin
    0.81
     shenan
    0.80
     perfet
    0.79
    Activations Density 0.140%

    No Known Activations