© 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. 252
    Prev
    Next
    INDEX
    Explanations

    dates and time-related information

    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
    +0.20
    1.0%
    776
    +0.16
    0.8%
    680
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.20
    0.11
    680
    +0.16
    0.08
    897
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.63
    /***
    -0.92
    Autoritní
    -0.82
    ///**
    -0.71
    <?
    -0.70
    
    -0.68
    /**
    -0.67
    /*!
    -0.66
    ⓧ
    -0.65
    //*/
    -0.63
    POSITIVE LOGITS
     lele
    1.12
     pican
    1.07
     maroc
    1.06
     gila
    1.01
     milano
    1.00
     italia
    1.00
     shopee
    0.98
     nuoc
    0.98
     ibiza
    0.98
     bandung
    0.97
    Activations Density 0.435%

    No Known Activations