© 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. 12364
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics, military operations, and historical events

    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
    1150
    +0.16
    0.5%
    1343
    +0.13
    0.4%
    1510
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.16
    0.03
    630
    +0.13
    0.04
    1962
    +0.12
    0.04
    Negative Logits
    pentru
    -0.77
    Și
    -0.72
    astéro
    -0.69
    Să
    -0.69
    Krok
    -0.69
     Statt
    -0.67
    Prí
    -0.66
    Kaip
    -0.65
    Dlaczego
    -0.65
    Kako
    -0.64
    POSITIVE LOGITS
     '.';
    0.65
     interposed
    0.62
     discontinuities
    0.62
     ".";
    0.59
     '-';
    0.59
    hermosa
    0.58
     logarith
    0.56
     ";"
    0.56
     "|"
    0.55
     مشين
    0.54
    Activations Density 0.048%

    No Known Activations