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

    Neuronpedia

    Jacobian LensNEW
    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. 6170
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical topics and relations

    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
    1048
    +0.07
    0.2%
    1120
    +0.07
    0.2%
    1499
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1048
    +0.07
    0.03
    939
    +0.07
    0.06
    1424
    +0.07
    0.05
    Negative Logits
     intersper
    -1.38
     apprehen
    -1.24
     accla
    -1.23
     depic
    -1.15
     fei
    -1.12
     disagre
    -1.08
     lele
    -1.07
     encomp
    -1.07
     noel
    -1.05
     reluct
    -1.04
    POSITIVE LOGITS
     presence
    0.71
     involvement
    0.64
    presence
    0.59
     investment
    0.56
     investments
    0.55
     invested
    0.54
     interest
    0.54
     intervention
    0.54
     invest
    0.53
    ']>;
    0.53
    Activations Density 0.572%

    No Known Activations