© 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. 4278
    Prev
    Next
    INDEX
    Explanations

    information related to technology and innovation, especially in the context of sustainability and energy efficiency

    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
    2034
    +0.25
    0.8%
    1535
    +0.18
    0.6%
    1699
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.11
    1535
    +0.18
    0.09
    310
    +0.15
    0.07
    Negative Logits
     Souha
    -1.03
     viciss
    -0.98
     acred
    -0.96
     كومونز
    -0.92
     Leurs
    -0.91
     Zwar
    -0.86
     Darum
    -0.84
     Ihm
    -0.84
     aussitôt
    -0.83
    ⓧ
    -0.83
    POSITIVE LOGITS
     However
    0.77
     But
    0.76
    ↵↵
    0.71
     Moreover
    0.66
     And
    0.66
     Furthermore
    0.66
    But
    0.66
     Therefore
    0.66
    However
    0.65
     Also
    0.64
    Activations Density 0.616%

    No Known Activations