© 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. 360
    Prev
    Next
    INDEX
    Explanations

    mentions of social concepts like social media, social service, and social inclusion

    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
    1.3%
    1870
    +0.13
    0.9%
    1828
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1125
    +0.20
    0.05
    501
    +0.13
    0.04
    1624
    +0.10
    0.05
    Negative Logits
    <bos>
    -3.35
    ⓧ
    -0.86
    /*++
    -0.76
    <?
    -0.76
    enumerate
    -0.72
     asked
    -0.70
    /**
    -0.68
     won
    -0.68
    for
    -0.68
    /**
    -0.68
    POSITIVE LOGITS
     Augu
    2.03
     aen
    1.96
     fta
    1.90
     Juf
    1.87
     affor
    1.87
     ftu
    1.84
     ftre
    1.80
     bandung
    1.79
     increa
    1.75
     Minang
    1.75
    Activations Density 0.090%

    No Known Activations