© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14299
    Prev
    Next
    INDEX
    Explanations

    lists or collections of items

    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
    227
    +0.13
    0.4%
    738
    +0.10
    0.3%
    674
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.13
    0.03
    441
    +0.10
    0.04
    1786
    +0.09
    0.01
    Negative Logits
     cytoplas
    -0.86
     tranf
    -0.86
     Traité
    -0.85
     Chapitre
    -0.85
     Aéroport
    -0.84
     Châ
    -0.83
     Mère
    -0.83
     lyon
    -0.81
     confider
    -0.81
     Sén
    -0.81
    POSITIVE LOGITS
     list
    1.14
     List
    0.96
     lists
    0.96
    list
    0.94
     lista
    0.89
     liste
    0.88
    List
    0.86
     listing
    0.79
     listings
    0.78
     список
    0.78
    Activations Density 0.623%

    No Known Activations