© 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. 14650
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and conflict within groups

    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
    50
    +0.11
    0.3%
    604
    +0.10
    0.3%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1664
    +0.11
    0.04
    332
    +0.10
    0.05
    16
    +0.10
    0.07
    Negative Logits
     shenan
    -1.00
     apprehen
    -0.95
     impra
    -0.92
     disreg
    -0.90
     swarovski
    -0.87
     hairc
    -0.86
     reluct
    -0.84
     scrat
    -0.83
     unspeak
    -0.83
     horrend
    -0.83
    POSITIVE LOGITS
    Gweler
    0.51
     injus
    0.51
    lň
    0.49
    Wart
    0.49
     noten
    0.47
     lack
    0.47
    Tür
    0.46
    ENOMEM
    0.46
     CiNii
    0.46
     handling
    0.46
    Activations Density 0.803%

    No Known Activations