© 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. 6621
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and ethics, particularly focused on the importance of basic human rights

    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
    1.2%
    1705
    +0.12
    0.7%
    680
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.21
    0.03
    680
    +0.12
    0.03
    1187
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.22
    /***
    -0.97
    //---
    -0.80
    ///**
    -0.74
    /*!
    -0.73
    <?
    -0.68
    //*/
    -0.67
    <!--
    -0.65
    /**
    -0.64
    ⓧ
    -0.63
    POSITIVE LOGITS
     santiago
    1.20
     maroc
    1.18
     napoli
    1.13
     milano
    1.11
     palio
    1.09
     wien
    1.08
     nomine
    1.08
     affez
    1.08
     italia
    1.06
     vasi
    1.04
    Activations Density 0.072%

    No Known Activations