© 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. 0-RES-JB
    11. 1436
    Prev
    Next
    INDEX
    Explanations

    information related to returns and exchanges, such as processes and policies, for various products

    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
    50
    +0.09
    0.3%
    1964
    +0.07
    0.2%
    31
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.09
    0.03
    559
    +0.07
    0.03
    303
    +0.06
    0.03
    Negative Logits
    ⓧ
    -1.07
    
    -0.99
     encomp
    -0.97
    <bos>
    -0.96
     intersper
    -0.96
    <?
    -0.90
    /**
    -0.84
     hentai
    -0.78
     hairc
    -0.77
     disreg
    -0.75
    POSITIVE LOGITS
     Returns
    1.23
    Returns
    1.20
     returns
    1.06
    returns
    0.93
     RETURNS
    0.88
    RETURNS
    0.75
     Backpack
    0.71
    celona
    0.67
     nuoc
    0.66
     ananas
    0.64
    Activations Density 0.126%

    No Known Activations