© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7493
    Prev
    Next
    INDEX
    Explanations

    statistics and demographic information related to minority groups, health, and economics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    856
    +0.16
    0.6%
    764
    +0.15
    0.6%
    50
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.16
    0.06
    1499
    +0.15
    0.06
    1380
    +0.14
    0.01
    Negative Logits
    <bos>
    -1.18
    IsContent
    -0.65
     Meksiku
    -0.56
    piram
    -0.55
    DoubleQuotes
    -0.55
     Seeder
    -0.52
    jsii
    -0.51
     Paglinawan
    -0.50
    TagMode
    -0.49
    twimg
    -0.49
    POSITIVE LOGITS
     Whence
    1.13
     Considerable
    1.03
     tolerably
    0.90
     Moderately
    0.84
     unlaw
    0.82
     unwarran
    0.81
     Middles
    0.81
     disagre
    0.80
     shenan
    0.79
     Lmao
    0.77
    Activations Density 0.599%

    No Known Activations