© 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. 343
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to Washington, DC

    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
    1272
    +0.16
    1.1%
    50
    +0.15
    1.0%
    874
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1272
    +0.16
    0.07
    874
    +0.15
    0.05
    1590
    +0.14
    0.04
    Negative Logits
    <bos>
    -3.26
    
    -1.10
    ⓧ
    -1.03
    <?
    -0.99
    /**
    -0.98
    <?
    -0.87
    /*
    -0.81
    /***
    -0.78
    HasIndex
    -0.72
     rehabilitate
    -0.66
    POSITIVE LOGITS
     Washington
    1.11
    Washington
    1.06
     mef
    1.06
     Châ
    1.04
     washington
    1.03
     isabel
    1.03
     wien
    1.01
     maroc
    1.01
     cioc
    1.01
     lele
    1.00
    Activations Density 0.070%

    No Known Activations