© 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. 13369
    Prev
    Next
    INDEX
    Explanations

    phrases that contain numbers or measurements

    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
    2034
    +0.25
    0.8%
    1535
    +0.20
    0.6%
    1699
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.11
    1535
    +0.20
    0.09
    1775
    +0.16
    0.08
    Negative Logits
     repug
    -1.07
     disagre
    -0.99
     suspic
    -0.99
     viciss
    -0.99
     Leurs
    -0.98
     pamph
    -0.97
     unwarran
    -0.95
     rodriguez
    -0.94
     Souha
    -0.93
     practition
    -0.92
    POSITIVE LOGITS
     These
    0.74
     Lastly
    0.72
     Finally
    0.71
    .‏
    0.69
    ↵↵
    0.68
     Both
    0.68
     This
    0.66
     Additionally
    0.66
    ConverterFactory
    0.65
    }.
    0.63
    Activations Density 0.509%

    No Known Activations