© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 323
    Prev
    Next
    INDEX
    Explanations

    present tense forms of the verb "to do" along with their context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.9%
    169
    +0.08
    0.3%
    889
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    312
    +0.23
    0.04
    305
    +0.08
    0.04
    315
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.76
    ///**
    -0.69
     &___
    -0.63
    //@
    -0.62
     rowspan
    -0.60
    ArrowToggle
    -0.60
    Vegeu
    -0.60
     khởi
    -0.59
    babel
    -0.59
    Referències
    -0.59
    POSITIVE LOGITS
     disreg
    1.52
     stockholm
    1.49
     maneu
    1.48
     outlander
    1.44
     madonna
    1.42
     milf
    1.41
     jaya
    1.41
     bangkok
    1.41
     maroc
    1.38
     jurassic
    1.36
    Activations Density 0.152%

    No Known Activations