© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 2037
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "except" followed by exceptions or qualifications

    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
    +0.20
    1.0%
    314
    +0.13
    0.7%
    866
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.20
    0.03
    890
    +0.13
    0.03
    1581
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.17
    ⓧ
    -0.78
    Vegeu
    -0.75
    public
    -0.73
     Roskov
    -0.73
    Enllaços
    -0.72
    widget
    -0.70
    job
    -0.69
    LinkedHashMap
    -0.69
    IsRequired
    -0.69
    POSITIVE LOGITS
     maneu
    1.91
     accla
    1.88
     fortn
    1.85
     volunte
    1.82
     disagre
    1.81
     stockholm
    1.79
     wien
    1.75
     impra
    1.75
     philanth
    1.75
     shenan
    1.72
    Activations Density 0.124%

    No Known Activations