© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6419
    Prev
    Next
    INDEX
    Explanations

    dialogue quotes and contractions

    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
    478
    +0.21
    1.3%
    2019
    +0.18
    1.1%
    1741
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.21
    0.17
    1224
    +0.18
    0.08
    2019
    +0.12
    0.13
    Negative Logits
    <bos>
    -3.34
     intersper
    -1.54
    /***
    -1.50
     hentai
    -1.47
     embra
    -1.41
     pessi
    -1.35
     suspic
    -1.31
     milf
    -1.30
    
    -1.29
     encre
    -1.29
    POSITIVE LOGITS
    '
    0.81
    ’
    0.80
    s
    0.63
    i
    0.60
    A
    0.60
    mathrm
    0.59
    S
    0.59
    An
    0.58
    I
    0.58
     
    0.57
    Activations Density 1.007%

    No Known Activations