© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2526
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and government appointments

    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
    453
    +0.11
    0.3%
    1177
    +0.10
    0.3%
    1042
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1600
    +0.11
    0.05
    1626
    +0.10
    0.04
    16
    +0.08
    0.05
    Negative Logits
     disreg
    -1.20
     scrat
    -1.03
     thermomix
    -0.94
     swarovski
    -0.94
     intersper
    -0.94
     peppa
    -0.94
     hairc
    -0.93
     pollut
    -0.93
     overcrow
    -0.93
     impra
    -0.91
    POSITIVE LOGITS
     president
    0.67
     head
    0.61
     CEO
    0.60
     vice
    0.59
     ambas
    0.58
     chairman
    0.58
     sole
    0.58
    Bibliograf
    0.58
     mayor
    0.57
     deputy
    0.57
    Activations Density 0.277%

    No Known Activations