© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7651
    Prev
    Next
    INDEX
    Explanations

    mentions of medical professionals, medical organizations, and related terms

    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
    227
    +0.12
    0.4%
    69
    +0.11
    0.3%
    283
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.07
    69
    +0.11
    0.03
    1082
    +0.09
    0.04
    Negative Logits
     coar
    -1.00
     tubercle
    -0.99
     osse
    -0.96
     labial
    -0.94
     cartila
    -0.94
     auricular
    -0.94
     lingual
    -0.86
     glandular
    -0.86
     sacro
    -0.85
     follic
    -0.83
    POSITIVE LOGITS
     physicians
    0.67
     physician
    0.64
     specializing
    0.60
     clinical
    0.56
     specialties
    0.55
     Medicina
    0.54
     Clinical
    0.54
     distrik
    0.53
     Occidente
    0.53
     clinicians
    0.53
    Activations Density 0.368%

    No Known Activations