© 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. 13429
    Prev
    Next
    INDEX
    Explanations

    mentions of technical terms related to digital currency and technology

    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
    1265
    +0.10
    0.3%
    2019
    +0.10
    0.3%
    1406
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1402
    +0.10
    0.02
    1406
    +0.10
    0.03
    1265
    +0.09
    0.03
    Negative Logits
     Outils
    -0.80
     Produits
    -0.67
     Spéc
    -0.67
     Matériau
    -0.66
     karton
    -0.66
     Entreprises
    -0.65
     antik
    -0.65
     Kategor
    -0.65
     Conseils
    -0.64
     Commentaires
    -0.64
    POSITIVE LOGITS
     ruddy
    0.76
     cuck
    0.75
     unspeak
    0.73
     profuse
    0.72
    /**
    0.72
     rascal
    0.68
     dusky
    0.68
     wolverine
    0.68
     gaily
    0.67
     tawny
    0.66
    Activations Density 0.139%

    No Known Activations