© 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. 12336
    Prev
    Next
    INDEX
    Explanations

    references to events and their impacts on individuals

    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
    2032
    +0.08
    0.2%
    1948
    +0.07
    0.2%
    1883
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2032
    +0.08
    0.04
    73
    +0.07
    0.02
    1431
    +0.07
    0.03
    Negative Logits
    Vidite
    -0.75
     pymysql
    -0.66
     smtplib
    -0.65
    addCriterion
    -0.64
    NameInMap
    -0.62
    DeleteBehavior
    -0.57
     dises
    -0.57
     hashlib
    -0.57
    jaja
    -0.57
     gend
    -0.56
    POSITIVE LOGITS
     currently
    0.62
     presently
    0.61
     current
    0.55
     now
    0.50
    attuale
    0.49
     curent
    0.47
     Ciò
    0.47
    current
    0.46
    currently
    0.46
    shampoo
    0.46
    Activations Density 0.168%

    No Known Activations