© 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. 12423
    Prev
    Next
    INDEX
    Explanations

    medical terms and discussions related to healthcare records or procedures

    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
    314
    +0.11
    0.3%
    1535
    +0.10
    0.3%
    872
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    0.04
    1984
    +0.10
    0.06
    868
    +0.10
    0.04
    Negative Logits
     quegli
    -0.69
    idać
    -0.63
     regardant
    -0.60
    vece
    -0.59
    ==""){
    -0.57
     onore
    -0.54
     virtù
    -0.54
    =="")
    -0.54
     Darauf
    -0.54
    troppo
    -0.53
    POSITIVE LOGITS
     cases
    1.07
     case
    0.94
    Cases
    0.88
    cases
    0.87
    case
    0.87
     Cases
    0.81
    Case
    0.81
     instances
    0.76
     situations
    0.74
     circumstances
    0.70
    Activations Density 0.275%

    No Known Activations