© 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. 6-RES-JB
    11. 225
    Prev
    Next
    INDEX
    Explanations

    nouns related to medical conditions, symptoms, and procedures

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    1.0%
    2034
    +0.11
    0.5%
    1438
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.21
    0.17
    1438
    +0.11
    0.12
    1385
    +0.10
    0.15
    Negative Logits
    <bos>
    -3.43
    /***
    -1.04
    /*++
    -0.80
     endow
    -0.80
    ///**
    -0.79
     intersper
    -0.77
     harmonize
    -0.72
    //{
    -0.69
     rehabilitate
    -0.68
     acquaint
    -0.67
    POSITIVE LOGITS
     mikrofon
    0.90
     déchir
    0.88
     silikon
    0.84
     étrang
    0.83
     Inhabitants
    0.83
     Momb
    0.81
     Keny
    0.81
     roul
    0.81
     lele
    0.80
     optik
    0.80
    Activations Density 2.618%

    No Known Activations