© 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. 6989
    Prev
    Next
    INDEX
    Explanations

    Linux commands and instructions related to configuring and running scripts

    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
    876
    +0.17
    0.5%
    1403
    +0.11
    0.3%
    511
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.17
    -0.00
    1511
    +0.11
    0.01
    1284
    +0.10
    0.03
    Negative Logits
     bakteri
    -0.93
     akade
    -0.90
     alkoh
    -0.88
     kriminal
    -0.86
     kosme
    -0.85
     kooper
    -0.85
     akut
    -0.84
     Demokrat
    -0.83
     panik
    -0.83
     Ukraina
    -0.82
    POSITIVE LOGITS
     affor
    0.97
     scrat
    0.97
     tupperware
    0.94
     affez
    0.92
     increa
    0.83
     philips
    0.82
     ikea
    0.82
     cushi
    0.81
     impra
    0.80
     oleo
    0.80
    Activations Density 0.197%

    No Known Activations