© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6611
    Prev
    Next
    INDEX
    Explanations

    references to Biblical figures, locations, and related terms, as well as names like "Luke" and numbers associated with Luke

    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
    1034
    +0.17
    0.8%
    1035
    +0.17
    0.8%
    871
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1177
    +0.17
    0.03
    227
    +0.17
    0.05
    981
    +0.17
    0.05
    Negative Logits
     كومونز
    -0.65
    QMetaType
    -0.52
     क्ष
    -0.50
    رشف
    -0.48
    styleType
    -0.48
    Demografía
    -0.45
    res
    -0.45
    PMailer
    -0.45
    createStatement
    -0.45
    Jäh
    -0.45
    POSITIVE LOGITS
     indestru
    0.95
     luke
    0.89
     intersper
    0.87
     sergio
    0.86
     impra
    0.84
     Mlle
    0.84
     accla
    0.83
     Docteur
    0.82
     eiffel
    0.82
     inappro
    0.81
    Activations Density 0.318%

    No Known Activations