© 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. 363
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex situations and legal 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.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
    +0.18
    1.2%
    2011
    +0.15
    1.0%
    1671
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2011
    +0.18
    0.03
    1671
    +0.15
    0.03
    468
    +0.14
    0.02
    Negative Logits
    <bos>
    -3.56
    /***
    -0.93
    ⓧ
    -0.81
    /*!
    -0.79
    #![
    -0.68
    //@
    -0.65
     expel
    -0.63
    /**
    -0.62
    //---
    -0.62
    /*++
    -0.62
    POSITIVE LOGITS
     shopee
    1.21
    situation
    1.19
     situation
    1.18
     situa
    1.10
    Situation
    1.08
     Situations
    1.08
     Situation
    1.07
     murano
    1.06
     stockholm
    1.06
     chrysler
    1.06
    Activations Density 0.067%

    No Known Activations