© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 146
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and scams

    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
    2015
    +0.09
    0.3%
    198
    +0.08
    0.2%
    1978
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2015
    +0.09
    0.03
    1385
    +0.08
    0.07
    1013
    +0.07
    0.07
    Negative Logits
     certainly
    -0.68
    Thông
    -0.64
     also
    -0.64
    ਿ
    -0.63
     could
    -0.63
    public
    -0.62
    ਿੱ
    -0.62
     perhaps
    -0.62
    ਹ
    -0.62
    adomo
    -0.62
    POSITIVE LOGITS
     ecru
    2.01
     swarovski
    1.96
     ftre
    1.94
     maneu
    1.89
     ftu
    1.87
     fta
    1.80
     thut
    1.72
     Khart
    1.71
     reft
    1.70
     affor
    1.70
    Activations Density 0.925%

    No Known Activations