© 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. 12046
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates 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
    1978
    +0.20
    0.6%
    1870
    +0.15
    0.5%
    227
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    994
    +0.20
    0.05
    382
    +0.15
    0.05
    1978
    +0.11
    0.06
    Negative Logits
    <bos>
    -0.79
    careous
    -0.66
     ویکی‌پدی
    -0.57
     demselben
    -0.57
     antwortete
    -0.57
    באנגלית
    -0.56
    richtet
    -0.55
    bình
    -0.55
    ഐ
    -0.55
     propOrder
    -0.55
    POSITIVE LOGITS
     makro
    1.10
     inev
    1.00
     Præ
    0.97
     antik
    0.97
     kram
    0.96
     Kategor
    0.96
     kön
    0.95
     keramik
    0.95
     optik
    0.94
     utop
    0.94
    Activations Density 0.305%

    No Known Activations