© 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. 6725
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of Moore's Law

    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
    629
    +0.14
    0.6%
    1515
    +0.14
    0.6%
    1222
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    629
    +0.14
    0.02
    981
    +0.14
    0.03
    1515
    +0.13
    0.01
    Negative Logits
     pitä
    -0.52
     esigenze
    -0.51
    حياتها
    -0.50
    ナツ
    -0.47
    okohama
    -0.46
    system
    -0.46
    sal
    -0.45
     Radcliffe
    -0.45
    FetchType
    -0.44
     Agnew
    -0.44
    POSITIVE LOGITS
     Moore
    1.48
    Moore
    1.41
     moore
    1.38
     MOORE
    1.30
     alberto
    0.98
     jorge
    0.92
     sergio
    0.90
     roberto
    0.89
     javier
    0.88
     sappi
    0.88
    Activations Density 0.133%

    No Known Activations