© 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. 6753
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values, such as amounts, percentages, and years

    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
    674
    +0.23
    0.8%
    1870
    +0.13
    0.4%
    1535
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.23
    0.07
    1839
    +0.13
    0.07
    1467
    +0.10
    0.04
    Negative Logits
     By
    -0.68
     Be
    -0.67
     More
    -0.66
     Most
    -0.65
     
    -0.65
     Many
    -0.64
     The
    -0.64
     My
    -0.63
     Good
    -0.63
     Oh
    -0.63
    POSITIVE LOGITS
     sappi
    1.69
     affez
    1.52
     soggior
    1.47
     peppa
    1.44
     canel
    1.42
     vito
    1.40
     milano
    1.40
     jorge
    1.39
     Luglio
    1.36
     Ottobre
    1.36
    Activations Density 0.906%

    No Known Activations