© 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. 12433
    Prev
    Next
    INDEX
    Explanations

    information related to political theories and movements focused on social and economic structures

    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
    1133
    +0.11
    0.4%
    1085
    +0.11
    0.3%
    732
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1133
    +0.11
    0.04
    1101
    +0.11
    0.03
    163
    +0.10
    0.02
    Negative Logits
    المصادر
    -0.55
    UnitTesting
    -0.54
    RTRS
    -0.50
    المراجع
    -0.47
    OOTD
    -0.46
     terrarium
    -0.45
    Américaine
    -0.43
    woor
    -0.43
     Course
    -0.42
     XLR
    -0.42
    POSITIVE LOGITS
     volon
    0.70
     hecta
    0.68
     maksi
    0.62
    🥲
    0.61
     doucement
    0.61
     🤣🤣
    0.61
    🤷
    0.60
    !!</
    0.59
     viciss
    0.59
     abbiano
    0.59
    Activations Density 0.066%

    No Known Activations