© 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. 4775
    Prev
    Next
    INDEX
    Explanations

    references to news sources, news events, and opinions in written content

    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
    1103
    +0.16
    0.8%
    1828
    +0.15
    0.7%
    1047
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.03
    1047
    +0.15
    0.03
    492
    +0.14
    0.03
    Negative Logits
     intersper
    -1.30
    <bos>
    -1.27
     shenan
    -1.24
     disagre
    -1.13
     unspeak
    -1.05
     apprehen
    -1.02
     milf
    -1.01
     hairc
    -0.99
     impelled
    -0.99
     gaily
    -0.97
    POSITIVE LOGITS
    CNN
    1.37
     CNN
    1.32
    cnn
    1.03
     cnn
    0.78
     CN
    0.73
    CN
    0.69
    PMailer
    0.66
     meras
    0.65
     amplific
    0.65
     parati
    0.62
    Activations Density 0.364%

    No Known Activations