© 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. 1972
    Prev
    Next
    INDEX
    Explanations

    physical books or literary genres like fiction literature

    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
    31
    +0.07
    0.2%
    1492
    +0.06
    0.2%
    866
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1291
    +0.07
    0.02
    1988
    +0.06
    0.02
    285
    +0.06
    0.02
    Negative Logits
    /*
    -0.71
    <bos>
    -0.69
    /**
    -0.67
    
    -0.64
    /*!
    -0.55
     prepare
    -0.54
     expand
    -0.54
    ⓧ
    -0.53
     also
    -0.53
     okhttp
    -0.52
    POSITIVE LOGITS
     fiction
    2.31
     Fiction
    2.08
    fiction
    1.90
    Fiction
    1.81
     FICTION
    1.77
     fictional
    1.49
     ficción
    1.37
     Minang
    1.37
     bandung
    1.25
     chèvre
    1.19
    Activations Density 0.149%

    No Known Activations