© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6531
    Prev
    Next
    INDEX
    Explanations

    mentions of American-related 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
    +0.21
    1.4%
    1984
    +0.13
    0.8%
    1323
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.21
    0.06
    636
    +0.13
    0.05
    1425
    +0.08
    0.04
    Negative Logits
    <bos>
    -3.57
    ⓧ
    -1.21
    /**
    -1.03
    
    
    -1.00
    <?
    -0.87
    /*
    -0.85
    /*++
    -0.78
    EndProject
    -0.75
    lateinit
    -0.74
    ValueGenerated
    -0.70
    POSITIVE LOGITS
     Juf
    1.77
     Châ
    1.64
     Traité
    1.57
     hcm
    1.57
     milano
    1.54
     Keny
    1.53
     véhic
    1.48
     mef
    1.47
     napoli
    1.47
     Minang
    1.45
    Activations Density 0.080%

    No Known Activations