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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 504
    Prev
    Next
    INDEX
    Explanations

    references to supernatural creatures, particularly zombies

    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
    1137
    +0.07
    0.2%
    555
    +0.07
    0.2%
    605
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.07
    0.02
    1252
    +0.07
    0.03
    1363
    +0.06
    0.03
    Negative Logits
    ⓧ
    -0.81
    <?
    -0.79
    <bos>
    -0.77
    __(/*!
    -0.73
    Dtor
    -0.65
    #
    -0.65
    Архівовано
    -0.64
    ///**
    -0.63
    Петер
    -0.62
    Seguro
    -0.59
    POSITIVE LOGITS
     maneu
    1.56
     wien
    1.51
     ftu
    1.51
     fta
    1.47
     marseille
    1.47
     bordeaux
    1.47
     indestru
    1.47
     aen
    1.47
     disagre
    1.46
     fte
    1.45
    Activations Density 0.243%

    No Known Activations