© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    identifiers such as URLs and dois within the text

    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
    +0.18
    0.6%
    453
    +0.08
    0.3%
    1379
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    937
    +0.18
    0.03
    1466
    +0.08
    0.03
    1684
    +0.08
    0.03
    Negative Logits
     solidar
    -0.86
     ideolog
    -0.81
     dè
    -0.77
     anse
    -0.75
     utop
    -0.75
     flot
    -0.73
    /**
    -0.73
    ⓧ
    -0.70
     permu
    -0.69
     baf
    -0.69
    POSITIVE LOGITS
    doi
    0.73
     doi
    0.73
     Apesar
    0.70
     KeyCode
    0.69
     soulign
    0.67
     Muitos
    0.66
     renfer
    0.65
     Hauteur
    0.64
     Embora
    0.64
     Estou
    0.64
    Activations Density 0.051%

    No Known Activations