© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 339
    Prev
    Next
    INDEX
    Explanations

    information related to viruses and medical research involving viruses

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    537
    +0.08
    0.3%
    1092
    +0.08
    0.3%
    517
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.08
    0.03
    517
    +0.08
    0.02
    144
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.10
    落
    -0.73
    ,
    -0.68
    大
    -0.68
    立
    -0.68
    เล
    -0.68
    補
    -0.67
    出
    -0.67
    周
    -0.67
     can
    -0.66
    POSITIVE LOGITS
     increa
    2.21
     affor
    2.15
     maneu
    2.15
     accla
    2.13
     effe
    2.04
     Virus
    2.03
     guarante
    2.01
     emphat
    2.01
     ftu
    1.98
     fath
    1.98
    Activations Density 0.171%

    No Known Activations