© 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. 0-RES-JB
    11. 1838
    Prev
    Next
    INDEX
    Explanations

    the word "ham."

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1404
    +0.09
    0.3%
    1994
    +0.07
    0.3%
    1328
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1550
    +0.09
    0.03
    1404
    +0.07
    0.03
    1152
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.29
    BUYER
    -0.67
    /***
    -0.61
    ੱਕ
    -0.60
     introduce
    -0.60
    (({
    -0.60
    └──
    -0.59
     grew
    -0.58
     continue
    -0.57
    ൊ
    -0.57
    POSITIVE LOGITS
     ham
    2.16
     Ham
    1.79
    Ham
    1.58
     HAM
    1.52
     stockholm
    1.49
     pollut
    1.37
     lidl
    1.36
     fta
    1.35
     sappi
    1.27
     toledo
    1.27
    Activations Density 0.144%

    No Known Activations