© 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. 2379
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and statements

    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
    184
    +0.12
    0.4%
    509
    +0.10
    0.3%
    1253
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.12
    0.06
    184
    +0.10
    0.02
    939
    +0.10
    0.05
    Negative Logits
     gmbh
    -0.88
     slan
    -0.78
     handels
    -0.75
     majest
    -0.70
     notori
    -0.70
     stik
    -0.69
     psycholog
    -0.69
     rangs
    -0.68
    ridescent
    -0.68
     pittores
    -0.68
    POSITIVE LOGITS
     Juf
    0.82
     Khart
    0.77
     Keny
    0.75
     shenan
    0.74
     unspeak
    0.72
     Momb
    0.71
     Inhabitants
    0.70
     Souha
    0.70
     Shakspeare
    0.69
     fornito
    0.68
    Activations Density 0.376%

    No Known Activations