© 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. 6466
    Prev
    Next
    INDEX
    Explanations

    sections indicating coding or programming-related discussions and instructions

    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
    82
    +0.17
    1.0%
    50
    +0.17
    1.0%
    597
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.17
    0.03
    1492
    +0.17
    0.03
    597
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.79
    EndProject
    -0.83
    contentLoaded
    -0.79
    <?
    -0.77
    ⓧ
    -0.71
    
    -0.70
    InputBorder
    -0.67
     розта
    -0.62
     gynhyrchwyd
    -0.60
    usermodel
    -0.60
    POSITIVE LOGITS
     tramont
    1.02
     maneu
    0.99
     maroc
    0.97
     catég
    0.96
     shenan
    0.93
     ananas
    0.91
     disreg
    0.90
     effray
    0.88
     scrat
    0.88
     toscana
    0.87
    Activations Density 0.057%

    No Known Activations