© 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. 12591
    Prev
    Next
    INDEX
    Explanations

    phrases related to being busy or occupied with tasks

    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
    1919
    +0.17
    0.5%
    381
    +0.16
    0.5%
    1415
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.17
    0.12
    1415
    +0.16
    0.08
    862
    +0.12
    0.03
    Negative Logits
     parlamento
    -1.29
     silikon
    -1.14
     hcm
    -1.07
     Politica
    -1.06
     Meksi
    -1.05
     balon
    -1.03
     keramik
    -1.03
     Quod
    -1.01
     demokra
    -1.00
     territo
    -0.99
    POSITIVE LOGITS
     myself
    1.01
    <bos>
    0.77
    myself
    0.75
    Cześć
    0.74
     my
    0.72
     feel
    0.71
     think
    0.71
     am
    0.70
     imagine
    0.67
     remember
    0.64
    Activations Density 0.618%

    No Known Activations