© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6456
    Prev
    Next
    INDEX
    Explanations

    information about various professions like collector, journalist, dealer, historian, photographer, screenwriter, activist, speaker, expert, minister, officer, lawyer, ecologist, researcher, hacker, critic, professor, and writer

    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
    1870
    +0.15
    0.4%
    1445
    +0.14
    0.4%
    16
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.15
    0.04
    356
    +0.14
    0.04
    227
    +0.12
    0.06
    Negative Logits
    VISIONS
    -0.77
    3
    -0.76
    2
    -0.75
    4
    -0.73
    8
    -0.73
    7
    -0.73
    5
    -0.71
    9
    -0.70
    6
    -0.70
     on
    -0.70
    POSITIVE LOGITS
     quoique
    1.91
     Ibidem
    1.89
     Souha
    1.83
     Cfr
    1.81
     Traité
    1.78
     Augu
    1.72
     Simult
    1.68
     Châ
    1.67
     Aéroport
    1.66
     Juf
    1.64
    Activations Density 0.209%

    No Known Activations