© 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. 319
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dick."

    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
    1757
    +0.18
    1.0%
    1618
    +0.16
    0.9%
    1828
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.18
    0.05
    437
    +0.16
    0.04
    1618
    +0.15
    0.03
    Negative Logits
    <bos>
    -1.28
    queryInterface
    -0.67
    nodoc
    -0.67
    res
    -0.67
     por
    -0.65
     res
    -0.62
    {~
    -0.61
    Datuak
    -0.61
    :+:
    -0.60
    AsUp
    -0.59
    POSITIVE LOGITS
     Dick
    1.51
    Dick
    1.49
     DICK
    1.37
     stockholm
    1.36
     Minang
    1.31
     bandung
    1.30
     olx
    1.25
     ibiza
    1.24
     tolerably
    1.23
     viciss
    1.23
    Activations Density 0.608%

    No Known Activations