© 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. 6685
    Prev
    Next
    INDEX
    Explanations

    terms related to Biblical locations and names, specifically focusing on Baalath-Beer and geographical details like "of the Negeb."

    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
    +0.15
    0.5%
    184
    +0.09
    0.3%
    1741
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2037
    +0.15
    0.05
    356
    +0.09
    0.04
    509
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.91
    public
    -0.93
    queryInterface
    -0.81
    tagHelper
    -0.81
    ว
    -0.80
    новниш
    -0.80
    :✨
    -0.80
    const
    -0.80
    fvar
    -0.79
     mergeFrom
    -0.79
    POSITIVE LOGITS
     emphat
    2.98
     increa
    2.92
     impra
    2.85
     maneu
    2.83
     reluct
    2.80
     fta
    2.80
     inev
    2.78
     fuf
    2.77
     affor
    2.75
     milf
    2.75
    Activations Density 0.225%

    No Known Activations