© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3630
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical events and political figures

    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
    680
    +0.16
    0.6%
    1137
    +0.12
    0.5%
    538
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.16
    0.04
    757
    +0.12
    0.04
    1137
    +0.12
    0.04
    Negative Logits
     chiedere
    -0.59
     Punj
    -0.53
    hamdu
    -0.52
    nene
    -0.51
     uscire
    -0.50
     Rov
    -0.49
     Ramadhan
    -0.49
     kasa
    -0.49
     Madura
    -0.48
     sentire
    -0.48
    POSITIVE LOGITS
    far
    1.08
    Far
    1.06
     Far
    1.04
     far
    1.03
     FAR
    1.02
    FAR
    0.99
     nutella
    0.70
     Février
    0.69
     jetta
    0.66
     swarovski
    0.65
    Activations Density 0.073%

    No Known Activations