© 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. 4120
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of political or social issues related to morality and public policy

    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
    198
    +0.12
    0.3%
    227
    +0.10
    0.3%
    1214
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.12
    0.06
    227
    +0.10
    0.07
    1870
    +0.08
    0.04
    Negative Logits
     êtres
    -0.89
     vété
    -0.89
     bénévoles
    -0.87
     ouvriers
    -0.81
     racon
    -0.80
     alliés
    -0.80
     cushi
    -0.80
     considér
    -0.79
     pères
    -0.77
     snoopy
    -0.77
    POSITIVE LOGITS
     keramik
    0.78
     kosme
    0.71
     minimalis
    0.70
     praktik
    0.69
     alkoh
    0.66
     subjek
    0.64
     akut
    0.61
     enthusiasts
    0.60
     kompati
    0.60
     konkre
    0.60
    Activations Density 0.485%

    No Known Activations