© 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. 13229
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments, particularly cancer

    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
    67
    +0.13
    0.4%
    1392
    +0.12
    0.4%
    1296
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.13
    0.02
    1392
    +0.12
    0.02
    890
    +0.11
    0.02
    Negative Logits
     disreg
    -0.66
     liberi
    -0.65
     PLW
    -0.63
     burberry
    -0.61
     dilap
    -0.60
     Squal
    -0.56
     quoique
    -0.54
     encomp
    -0.54
    indsay
    -0.53
     claudia
    -0.53
    POSITIVE LOGITS
     cancer
    1.33
    Cancer
    1.22
    cancer
    1.21
     Cancer
    1.19
     CANCER
    1.04
     cancers
    0.98
     tumor
    0.87
    áncer
    0.78
     saar
    0.78
     onco
    0.77
    Activations Density 0.061%

    No Known Activations