© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    medical symptoms and conditions

    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
    468
    +0.17
    0.6%
    370
    +0.14
    0.5%
    196
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.17
    0.02
    370
    +0.14
    0.02
    257
    +0.10
    0.02
    Negative Logits
     interro
    -0.67
     €€
    -0.62
     cento
    -0.57
     discogs
    -0.56
     aspi
    -0.56
     brilla
    -0.56
     pensa
    -0.56
    ceptives
    -0.55
     sape
    -0.55
     utop
    -0.55
    POSITIVE LOGITS
     symptoms
    1.25
     symptom
    1.19
     Symptoms
    1.13
    Symptoms
    1.07
    symptoms
    1.06
     Symptom
    0.94
     sympy
    0.86
     symptomatic
    0.82
    Symptom
    0.81
     SYMP
    0.77
    Activations Density 0.071%

    No Known Activations