© 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. 6511
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a critical moment or brink of a significant event

    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
    674
    +0.09
    0.2%
    612
    +0.08
    0.2%
    605
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.09
    0.04
    1759
    +0.08
    0.04
    1041
    +0.08
    0.03
    Negative Logits
     jard
    -0.48
     patrie
    -0.47
    piram
    -0.45
     porsi
    -0.45
     llu
    -0.43
     recomand
    -0.42
    cupa
    -0.41
     محفوظة
    -0.41
     Busca
    -0.40
     Défense
    -0.39
    POSITIVE LOGITS
     dirait
    0.68
     raggiunto
    0.63
     remarqué
    0.63
     préfère
    0.63
     persino
    0.61
     addirittura
    0.61
     regardant
    0.61
     precipice
    0.59
     tanga
    0.59
    ientôt
    0.58
    Activations Density 0.334%

    No Known Activations