© 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. 2399
    Prev
    Next
    INDEX
    Explanations

    references to Brazilian and Nigerian entities or terms

    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
    +0.12
    0.7%
    752
    +0.04
    0.2%
    1984
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1252
    +0.12
    0.10
    1319
    +0.04
    0.09
    683
    +0.04
    0.08
    Negative Logits
    <bos>
    -1.46
    public
    -0.96
     continue
    -0.95
    ⓧ
    -0.95
     put
    -0.92
    /**
    -0.90
    ,
    -0.88
    //
    -0.88
     so
    -0.87
    /**
    -0.87
    POSITIVE LOGITS
     affor
    2.90
     increa
    2.82
     Juf
    2.72
     maneu
    2.67
     accla
    2.62
     inev
    2.58
     disagre
    2.57
     stockholm
    2.56
     guarante
    2.56
     wherea
    2.55
    Activations Density 0.252%

    No Known Activations