© 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. 12531
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and government processes

    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
    1499
    +0.14
    0.4%
    453
    +0.11
    0.3%
    1257
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.14
    0.05
    1307
    +0.11
    0.03
    213
    +0.08
    0.04
    Negative Logits
     indestru
    -1.84
     hairc
    -1.78
     ecru
    -1.73
     impra
    -1.71
     swarovski
    -1.70
     intersper
    -1.70
     inconce
    -1.66
     increa
    -1.63
     depic
    -1.63
     unspeak
    -1.61
    POSITIVE LOGITS
    principalColumn
    0.74
     gynhyrchwyd
    0.72
     typelib
    0.66
    ьаж
    0.65
    دانشنامهٔ
    0.63
    Tazama
    0.62
    AntiForgeryToken
    0.62
    QMetaType
    0.61
    WebKit
    0.61
    CloseOperation
    0.60
    Activations Density 0.220%

    No Known Activations