© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12647
    Prev
    Next
    INDEX
    Explanations

    references to rumors and leaks about various topics, potentially related to technology or politics

    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
    1137
    +0.12
    0.4%
    1092
    +0.10
    0.3%
    1363
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1137
    +0.12
    0.03
    1525
    +0.10
    0.02
    1425
    +0.10
    0.02
    Negative Logits
     ciment
    -0.67
     canne
    -0.66
     proie
    -0.66
     impon
    -0.66
     alfabe
    -0.65
     itali
    -0.63
     intit
    -0.61
     inso
    -0.60
     quí
    -0.60
     Ressource
    -0.60
    POSITIVE LOGITS
     rumor
    1.18
     rumors
    1.17
     rumours
    1.07
     rumour
    1.03
     Rumors
    0.99
     rumored
    0.95
    Rumors
    0.88
     rumoured
    0.86
     murmuring
    0.83
     quitted
    0.82
    Activations Density 0.103%

    No Known Activations