© 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. 6628
    Prev
    Next
    INDEX
    Explanations

    references to distinguished or notable individuals such as professors

    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
    871
    +0.13
    0.5%
    1339
    +0.12
    0.4%
    479
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1654
    +0.13
    0.03
    1339
    +0.12
    0.02
    1194
    +0.12
    0.02
    Negative Logits
     createDate
    -0.66
     purplish
    -0.64
     eventId
    -0.64
     prêtre
    -0.57
     friable
    -0.57
     andreas
    -0.57
     currentIndex
    -0.56
     nicolas
    -0.55
     rodriguez
    -0.55
     dahlia
    -0.55
    POSITIVE LOGITS
     professor
    1.20
     Professor
    1.17
    Professor
    1.08
    professor
    1.05
     professors
    1.02
     Prof
    0.92
     prof
    0.89
     Professors
    0.88
     Profesor
    0.85
    Prof
    0.83
    Activations Density 0.057%

    No Known Activations