© 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. 2244
    Prev
    Next
    INDEX
    Explanations

    information related to technical setup and configuration steps

    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
    1978
    +0.17
    0.5%
    382
    +0.12
    0.4%
    1150
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.17
    0.04
    994
    +0.12
    0.03
    82
    +0.11
    0.03
    Negative Logits
    født
    -0.59
    احث
    -0.58
    ADELPHIA
    -0.57
    会话
    -0.57
     finnas
    -0.55
    徊
    -0.55
     jScrollPane
    -0.54
    собен
    -0.54
    Chúng
    -0.54
     протяжении
    -0.54
    POSITIVE LOGITS
     increa
    2.04
     suscep
    1.98
     impra
    1.96
     reluct
    1.90
     unden
    1.89
     disagre
    1.87
     inev
    1.85
     maneu
    1.83
     inappro
    1.83
     encomp
    1.79
    Activations Density 0.157%

    No Known Activations