© 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. 2515
    Prev
    Next
    INDEX
    Explanations

    patterns related to formatting and user input

    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
    405
    +0.08
    0.3%
    1328
    +0.08
    0.3%
    1573
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.08
    0.03
    975
    +0.08
    0.03
    1357
    +0.08
    0.03
    Negative Logits
     conspired
    -0.54
     belangrij
    -0.52
     strangled
    -0.50
    ValueGeneration
    -0.50
     inaugurate
    -0.49
     pled
    -0.49
    ///**
    -0.48
     overthrown
    -0.48
     plundered
    -0.47
     knelt
    -0.47
    POSITIVE LOGITS
     tab
    2.99
     Tab
    2.79
    Tab
    2.53
     tabs
    2.50
    tab
    2.36
     TAB
    2.24
     Tabs
    2.17
    TAB
    2.03
    tabs
    1.90
    Tabs
    1.85
    Activations Density 0.177%

    No Known Activations