© 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. 0-RES-JB
    11. 589
    Prev
    Next
    INDEX
    Explanations

    mentions of a person's name "Lon" with varying numbers next to the name

    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
    31
    +0.12
    0.4%
    1323
    +0.11
    0.4%
    1023
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.12
    0.05
    31
    +0.11
    0.04
    1343
    +0.10
    0.05
    Negative Logits
    <bos>
    -0.87
    usercontent
    -0.64
     raise
    -0.62
    parseColor
    -0.60
    insertBefore
    -0.60
    Tuy
    -0.60
     viewWillAppear
    -0.60
    עי
    -0.59
    一
    -0.58
    摘要
    -0.58
    POSITIVE LOGITS
     emphat
    1.80
     sappi
    1.76
     lyon
    1.73
     maneu
    1.71
     secon
    1.68
     wien
    1.67
     affor
    1.66
     coö
    1.65
     stockholm
    1.61
     effe
    1.60
    Activations Density 0.257%

    No Known Activations