© 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. 6585
    Prev
    Next
    INDEX
    Explanations

    verbs expressing obligation or necessity

    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
    204
    +0.27
    1.1%
    478
    +0.14
    0.6%
    1068
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.27
    0.06
    411
    +0.14
    0.04
    1265
    +0.13
    0.04
    Negative Logits
    GRU
    -0.60
    Tren
    -0.57
    Grup
    -0.57
     Sc
    -0.56
     Gra
    -0.55
    Fe
    -0.55
     Sh
    -0.55
    Di
    -0.55
    Sc
    -0.54
    Pu
    -0.54
    POSITIVE LOGITS
     tramont
    1.11
     sergio
    1.09
     [''
    1.03
     loginUser
    1.01
     nicolas
    1.01
     roberto
    1.00
     javier
    0.99
     bambina
    0.95
     alberto
    0.95
     blackpink
    0.94
    Activations Density 0.444%

    No Known Activations