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

    Neuronpedia

    Jacobian LensNEW
    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. 10889
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of equipment or facilities, particularly in the context of space exploration or healthcare

    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
    946
    +0.11
    0.3%
    334
    +0.11
    0.3%
    1462
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.05
    69
    +0.11
    0.01
    334
    +0.10
    0.04
    Negative Logits
     maroc
    -0.63
     nutr
    -0.60
     grig
    -0.59
     angelo
    -0.59
     franz
    -0.59
     compil
    -0.58
     pyram
    -0.58
     malin
    -0.58
     daz
    -0.58
     baum
    -0.57
    POSITIVE LOGITS
     medical
    0.69
    OSPITAL
    0.68
     hospitals
    0.68
    bateria
    0.67
     hospital
    0.67
     healthcare
    0.64
    Sklici
    0.62
     ambulance
    0.57
     emergency
    0.57
     Hospital
    0.55
    Activations Density 0.495%

    No Known Activations