© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7655
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments

    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
    1842
    +0.11
    0.3%
    1217
    +0.11
    0.3%
    1589
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1217
    +0.11
    0.03
    509
    +0.11
    0.03
    942
    +0.08
    0.02
    Negative Logits
     auricular
    -0.66
     osse
    -0.64
     PLW
    -0.63
     osteo
    -0.61
     follic
    -0.59
     synap
    -0.58
     antem
    -0.57
     mercantile
    -0.57
     diarr
    -0.55
     Whigs
    -0.55
    POSITIVE LOGITS
     cancer
    0.71
    Cancer
    0.63
     Cancer
    0.62
    cancer
    0.59
     tumor
    0.57
    arcoma
    0.56
     chemotherapy
    0.55
     onco
    0.53
    oblastoma
    0.52
     cancers
    0.52
    Activations Density 0.190%

    No Known Activations