© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2416
    Prev
    Next
    INDEX
    Explanations

    mentions of specific historical events, organizations, and leagues related to the World Cup and military conflicts

    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
    812
    +0.13
    0.5%
    597
    +0.13
    0.5%
    1505
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1505
    +0.13
    0.04
    1828
    +0.13
    0.04
    1793
    +0.13
    0.04
    Negative Logits
     initComponents
    -0.54
    <bos>
    -0.53
     chví
    -0.51
    zzlies
    -0.50
     esternos
    -0.47
    ništvo
    -0.45
    aarrggbb
    -0.45
     "..\..\
    -0.45
    viable
    -0.44
    bisoft
    -0.43
    POSITIVE LOGITS
     World
    1.17
    World
    1.13
     Áng
    1.02
    WORLD
    0.99
     Cuen
    0.98
     WORLD
    0.97
     Darío
    0.93
     Söz
    0.92
     Gorb
    0.90
    Worlds
    0.89
    Activations Density 0.072%

    No Known Activations